A method and system for fire point recognition based on satellite images

Abstract

The present invention provides a method and system for fire point recognition based on satellite images, which relates to the technical field of fire point recognition. The method includes: obtaining satellite attitude and orbit data when collecting satellite images; establishing fast conversion parameters for converting the coordinates of each pixel point in the satellite image into pixel point coordinates in the pixel coordinate system; using the fast conversion parameters to convert the image coordinates of each part of the satellite image into world coordinates in the geocentric coordinate system; obtaining the longitude and latitude of each world coordinate of the satellite image in the geocentric coordinate system according to the world coordinates; converting the brightness value of the pixel point to be detected in the satellite image into radiation brightness temperature; when the radiation brightness temperature is greater than the radiation brightness temperature threshold set according to the longitude and latitude, determining the pixel point to be detected as an initial fire point; performing a primary screening on the initial fire point according to the radiation brightness temperature difference value of the pixel point to be detected at different radiation wavelengths; and performing a secondary screening on the initial fire point after the primary screening in the cloud and water body area in combination with the fast conversion parameters to retain the target fire point.

Description

Technical Field

[0001] The present invention relates to the technical field of fire point recognition, and particularly to a fire point recognition method and system based on satellite images. Background Art

[0002] Fire point recognition based on satellite images is a technology that uses image data captured by satellite sensors to detect surface fires (such as forest fires or grassland fires). This method mainly determines whether there are fire points on the surface by analyzing satellite image information. Fire point recognition based on satellite images has the significant advantages of wide coverage and fast response speed, and can monitor the fire situation in remote and inaccessible areas in real time, which plays a crucial role in early fire detection, timely mobilization of rescue resources, and reduction of losses caused by fires.

[0003] Currently, in the process of fire point recognition based on satellite images, it is often directly determined whether it is a fire point by determining the radiance temperature of the satellite image. However, this method cannot exclude the influence of interference such as warm background, cloud bodies, and water bodies, resulting in large errors and being prone to misjudgment, thus limiting its practicality. Summary of the Invention

[0004] In order to solve the technical problems existing in the prior art that in the process of fire point recognition based on satellite images, it is often directly determined whether it is a fire point by determining the radiance temperature of the satellite image, but this method cannot exclude the influence of interference such as warm background, cloud bodies, and water bodies, resulting in large errors and being prone to misjudgment, thus limiting its practicality, the present invention provides a fire point recognition method and system based on satellite images.

[0005] The technical solutions provided by the embodiments of the present invention are as follows:

[0006] First Aspect

[0007] A fire point recognition method based on satellite images provided by an embodiment of the present invention includes:

[0008] S1: Obtain the satellite attitude and orbit data corresponding to the acquisition of the satellite image, where the satellite attitude and orbit data include the satellite speed at the exposure moment, the satellite position at the exposure moment, and the satellite attitude angle at the exposure moment;

[0009] S2: Combine the satellite attitude and orbit data to establish fast conversion parameters for converting the coordinates of each pixel point in the satellite image into the coordinates of pixel points in the pixel coordinate system, where the fast conversion parameters include the coordinates of the center point of the satellite image in the pixel coordinate system and the length of a single pixel point in the satellite image in each coordinate axis direction of the image coordinate system;

[0010] S3: Use the fast conversion parameters to convert the respective image coordinates of the satellite image into world coordinates in the geocentric coordinate system;

[0011] S4: Obtain the longitude and latitude of each world coordinate of the satellite image in the geocentric coordinate system according to the world coordinates;

[0012] S5: Convert the brightness value of the pixel point to be detected in the satellite image into radiance brightness temperature;

[0013] S6: When the radiance brightness temperature is greater than the radiance brightness temperature threshold set according to the longitude and latitude, determine the pixel point to be detected as an initial fire point;

[0014] S7: Perform a primary screening on the initial fire points according to the radiance brightness temperature difference value of the pixel point to be detected at different radiation wavelengths;

[0015] S8: Combine the fast conversion parameters to perform a secondary screening of the cloud and water body regions for the initial fire points after the primary screening, and retain the target fire points.

[0016] Second aspect

[0017] A fire point recognition system based on satellite images provided by an embodiment of the present invention includes:

[0018] A processor;

[0019] A memory, on which computer-readable instructions are stored, and when the computer-readable instructions are executed by the processor, the fire point recognition method based on satellite images as described in the first aspect is implemented.

[0020] Third aspect

[0021] A computer-readable storage medium provided by an embodiment of the present invention, on which a computer program is stored, and when the program is executed by a processor, the fire point recognition method based on satellite images as described in the first aspect is implemented.

[0022] The beneficial effects brought by the technical solutions provided by the embodiments of the present invention at least include:

[0023] In the present invention, first, in combination with the satellite attitude and orbit data, fast conversion parameters for converting the coordinates of each pixel point in the satellite image into the coordinates of the pixel point in the pixel coordinate system are established, so as to effectively and quickly filter out irrelevant interferences at the pixel point level. After initially determining the initial fire points through the radiance brightness temperature, a primary screening is performed using the radiance brightness temperature difference of the satellite at different radiation wavelengths to eliminate false fire points caused by warm backgrounds, and the cloud and water body regions are determined using the obtained coordinate conversion parameters, and further remove the initial fire points after the primary screening belonging to the cloud and water body regions to obtain more accurate fire points, further reducing the fire point misjudgment rate and increasing the practicability of fire point recognition based on satellite images. Description of the drawings

[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0025] Figure 1 It is a schematic flowchart of a method for identifying fire points based on satellite images provided by an embodiment of the present invention;

[0026] Figure 2 It is a schematic structural diagram of a system for identifying fire points based on satellite images provided by an embodiment of the present invention. Specific embodiments

[0027] The following will describe the technical solutions in the present invention with reference to the drawings.

[0028] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as an "example" in the present invention should not be construed as being more preferred or more advantageous than other embodiments or design solutions. Exactly speaking, the use of the word "example" is intended to present concepts in a specific manner. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or either of the two can be selected.

[0029] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference is not emphasized, the meanings they express are the same. "(of)", "corresponding", and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference is not emphasized, the meanings they express are the same.

[0030] In the embodiments of the present invention, sometimes subscripts such as W 1 may be miswritten as non-subscript forms such as W1. When the difference is not emphasized, the meanings they express are the same.

[0031] To make the technical problems, technical solutions and advantages to be solved by the present invention clearer, the following will be described in detail with reference to the drawings and specific embodiments.

[0032] Referring to the attached specification Figure 1 shows a schematic flowchart of a method for identifying fire points based on satellite images provided by an embodiment of the present invention.

[0033] An embodiment of the present invention provides a method for identifying fire points based on satellite images. This method can be implemented by a fire point identification device based on satellite images, and the fire point identification device based on satellite images can be a terminal or a server. The processing flow of the method for identifying fire points based on satellite images may include the following steps:

[0034] S1: Obtain the satellite attitude and orbit data corresponding to the acquisition of the satellite image.

[0035] Among them, the satellite attitude and orbit data include the satellite speed at the exposure moment, the satellite position at the exposure moment, and the satellite attitude angle at the exposure moment.

[0036] Among them, the satellite speed at the exposure moment refers to the moving speed of the satellite at the exact moment of capturing the image. Understanding the satellite's speed can help analyze the motion blur in the satellite image and is very important for subsequent image correction and processing. The satellite position at the exposure moment refers to the exact spatial position of the satellite during image capture. This information is extremely crucial for determining the geographical locations corresponding to each pixel in the image, especially when performing ground feature positioning and range estimation. The satellite attitude angle at the exposure moment refers to the specific orientation or angle of the satellite relative to the Earth. The attitude angle of the satellite affects the orientation and coverage area of the image and is particularly important for the geometric correction and analysis accuracy of the image. Obtaining these attitude and orbit data enables more accurate analysis of the satellite image, helps extract more reliable information from the image, such as terrain analysis, object recognition, etc. In remote sensing technology, the speed, position, and attitude data of the satellite are crucial for ensuring the consistency between the image and the actual ground situation and are the basis for high-quality image processing and analysis.

[0037] S2: Combine the satellite attitude and orbit data to establish fast conversion parameters for converting the coordinates of each pixel point in the satellite image into the coordinates of pixel points in the pixel coordinate system.

[0038] Among them, the fast conversion parameters include the coordinates of the center point of the satellite image in the world coordinate system and the length of a single pixel point in the satellite image in each coordinate axis direction of the image coordinate system.

[0039] Among them, obtaining the fast conversion parameters helps convert these coordinates into the coordinates in the pixel coordinate system. The core purpose of this step is to achieve accurate correspondence and fast conversion of coordinates for facilitating image analysis and processing.

[0040] In a possible implementation manner, S2 specifically includes:

[0041] S201: Determine the coordinates of the four corner points and the center point in the satellite image.

[0042] S202: Obtain the corresponding corner world coordinates and center point world coordinates in the world coordinate system for the corner point coordinates and the center point coordinates according to the satellite attitude and orbit data.

[0043] S203: Substitute the obtained corner world coordinates and center point world coordinates into the correlation equation between the world coordinate system and the image coordinate system to solve for the fast conversion parameters. The specific correlation equation is as follows:

[0044]

[0045] Among them, (X, Y) represents the world coordinates, I and J respectively represent the row number and column number of the pixel points of the satellite image, (x0, y0) represents the center point world coordinates, w and h respectively represent the width and height of the satellite image, and dx and dy respectively represent the lengths of a single pixel point of the satellite image in the X-axis direction and Y-axis direction in the image coordinate system.

[0046] Specifically, first determine the four corner points (upper left, upper right, lower left, lower right) in the satellite image and the center point coordinates of the image. These coordinates are usually positions in the pixel coordinate system and are used to establish the relationship between the image and the actual geographical location. According to the attitude and position data of the satellite, convert the pixel coordinates in the image determined in S201 into the corresponding world coordinates, and convert the pixel positions into the actual geographical locations (such as longitude, latitude, altitude). This conversion mainly depends on the real-time attitude and orbit data of the satellite. Substitute the world coordinates and image coordinates obtained from S202 into a predefined correlation equation to solve for the required fast conversion parameters. The solution of these parameters involves corresponding the position of each pixel point in the image with its actual position on the earth, so as to make the conversion from image coordinates to world coordinates fast and accurate.

[0047] In the actual application process, first obtain the satellite's current moment coordinates, then obtain the three attitude angles of the satellite. Use the three attitude angles and the attitude equivalent matrix to find the direction vector of the z-axis of the satellite sensor. Use the satellite's current moment coordinates to construct a straight line and find the intersection point with the earth ellipsoid equation, and then obtain the distance from the imaging center of the satellite image converted to the coordinates in the sensor coordinate system to the ground object. According to the equivalent matrix after satellite geometric calibration and the obtained distance from the imaging center to the ground object, find the coordinates of the four corner points and the center point of the satellite image in the sensor coordinate system, then convert them to the coordinates in the orbit coordinate system, and finally convert them to the world coordinates in the geocentric coordinate system, i.e., the WGS82 coordinate system. According to the obtained world coordinates, obtain the corresponding geodetic coordinates, and based on the obtained geodetic coordinates, the positioning fast conversion parameters can be calculated.

[0048] S3: Use the fast conversion parameters to convert each image coordinate of the satellite image into the world coordinates in the geocentric coordinate system.

[0049] In a possible implementation manner, S3 specifically includes:

[0050] S301: Convert the image coordinates to pixel coordinates in the pixel coordinate system using the fast conversion parameters.

[0051]

[0052] Among them, (x, y) represents the image coordinates.

[0053] S302: Combine the internal orientation element matrix of the satellite infrared payload to calculate the sensor coordinates of the satellite image in the sensor coordinate system.

[0054]

[0055] Among them, f λ represents the focal length of the infrared camera in the corresponding band, and (x'0, y'0) represents the coordinates of the principal point in the image plane.

[0056] S303: Combine the attitude equivalent matrix at the satellite exposure time to calculate the orbital coordinates of the image coordinates in the orbital coordinate system and convert the orbital coordinates to world coordinates.

[0057] S304: Calculate the world coordinates of the image coordinates according to the conversion matrix between the orbital coordinate system and the geocentric coordinate system:

[0058]

[0059] Among them, represents the world coordinates of the image coordinates, and R T represents the conversion matrix.

[0060] It should be noted that by using the fast conversion parameters, the internal orientation element matrix, the attitude equivalent matrix, and the coordinate system conversion matrix, this process can accurately correspond the image data to the actual geographical location. This conversion not only enhances the spatial accuracy of the image data but also improves the automation and efficiency of data processing.

[0061] S4: Obtain the longitude and latitude of each world coordinate of the satellite image in the geocentric coordinate system according to the world coordinates.

[0062] In a possible implementation manner, the specific method for obtaining the longitude and latitude of each world coordinate of the satellite image in the geocentric coordinate system by the world coordinates is as follows:

[0063]

[0064] Among them, α represents the longitude and β represents the latitude.

[0065] Among them, longitude and latitude are coordinate systems used to determine any position on the Earth's surface. Since there are differences in the radiation brightness temperature at different latitudes, the longitude and latitude calculated through accurately obtained world coordinates can accurately determine the radiation brightness temperature threshold, thereby making the result of fire point discrimination based on radiation brightness temperature more accurate and reliable.

[0066] S5: Convert the brightness value of the pixel to be detected in the satellite image into radiation brightness temperature.

[0067] Among them, the brightness value is also called the DN value. The DN value (Digital Number) is the brightness value of the pixel in the remote sensing image, recording the gray scale of the ground object. The radiation brightness temperature refers to the temperature of the electromagnetic radiation emitted by an object, which is an apparent temperature estimated based on the radiation intensity emitted by the object. This concept is based on the blackbody radiation theory, where an ideal blackbody is an object that completely absorbs all incident radiation and completely emits radiation. In practical applications, the radiation brightness temperature is used to describe the thermal radiation ability of the object surface, rather than necessarily the actual physical temperature of the object.

[0068] It should be noted that the step of converting the DN value in the satellite image into radiation brightness temperature is crucial for deeply understanding the surface thermal characteristics and environmental conditions. This conversion enables scientists and analysts to obtain accurate information about the surface temperature from remote sensing data.

[0069] In a possible implementation manner, the radiation brightness temperature is specifically:

[0070]

[0071] Among them, T represents the radiation brightness temperature, b represents the Wien displacement constant, λ represents the radiation wavelength, ln represents the natural logarithm, L(λ) represents the radiance L at the given radiation wavelength λ, h represents the Planck constant, c represents the speed of light, k represents the Boltzmann constant, G represents the calibration slope, B represents the calibration intercept, DN represents the brightness value of the pixel to be detected, and e represents the base of the natural logarithm.

[0072] It should be noted that the calculated radiation brightness temperature is for analyzing surface thermal characteristics, monitoring environmental changes, obtaining information about the Earth's environmental conditions and changes, and evaluating the impact of disasters (such as fires).

[0073] S6: When the radiation brightness temperature is greater than the radiation brightness temperature threshold set according to the longitude and latitude, determine the pixel to be detected as an initial fire point.

[0074] It should be noted that considering the significant differences in the environmental and climatic conditions on the Earth's surface at different geographical locations, for example, factors such as the vegetation type, aridity or humidity, and seasonal changes in different regions may affect the normal ground temperature. Therefore, by setting different radiative brightness temperature thresholds for different latitudes and longitudes, the true fire points can be identified more accurately, avoiding misjudgments caused by environmental factors, such as mistaking a high-temperature rock surface or high temperature caused by direct sunlight as a fire point. Such a setting enhances the applicability and accuracy of the fire point detection technology. The radiative brightness temperature of each pixel in the satellite image is compared with the threshold associated with a specific latitude and longitude. If the radiative brightness temperature of a certain pixel exceeds this threshold, this pixel is initially identified as a fire point. This step is based on setting different radiative brightness temperature thresholds according to geographical locations, thereby improving the accuracy and adaptability of fire point identification, especially under different geographical environments and climatic conditions.

[0075] It should be noted that those skilled in the art can set the magnitude of the radiative brightness temperature threshold according to actual needs, and the present invention does not limit this here.

[0076] S7: Perform a primary screening of the initial fire points based on the radiative brightness temperature difference of the pixel points to be detected at different radiative wavelengths.

[0077] Among them, the radiative brightness temperature difference refers to the difference in the brightness temperature readings at the same location under different infrared bands. A real flame usually shows a higher brightness temperature than the surrounding non-combustion area in specific infrared bands (such as the mid-infrared band). This is because the thermal radiation intensity of the flame is higher than that of the general natural background. The method based on the radiative brightness temperature difference is mainly used to eliminate false fire points caused by a warm background based on the significant temperature difference between the flame and its surrounding environment in the infrared spectrum. The flame will generate very high radiation energy in certain infrared bands, which results in a significantly higher radiative brightness temperature than the areas without a flame around. By comparing the radiative brightness temperature differences at the same location under different infrared bands, the true fire points are effectively screened out. This method utilizes the unique radiation characteristics of the flame in specific infrared bands, which are significantly higher than the surrounding environment, thereby eliminating high-temperature false alarms caused by natural warm backgrounds or other non-fire source factors. This screening mechanism enhances the accuracy of fire point detection, reduces false alarms, and improves the reliability and practicality of the fire point monitoring system.

[0078] In a possible implementation manner, S7 specifically includes:

[0079] S701: Obtain the radiative brightness temperature difference of the pixel points to be detected under two bands with different radiative wavelengths.

[0080] S702: Determine whether the current moment belongs to day or night. If the current moment is daytime, proceed to S703; otherwise, proceed to S704.

[0081] S703: When the radiative brightness temperature difference is greater than the first brightness temperature difference threshold, retain the initial fire point corresponding to the pixel to be detected.

[0082] S704: When the radiative brightness temperature difference is greater than the second brightness temperature difference threshold, retain the initial fire point corresponding to the pixel to be detected.

[0083] It should be noted that the different criteria for the brightness temperature difference between day and night mainly take into account the influence of solar radiation under sunlight conditions. During the day, solar radiation increases the surface temperature of the ground and other objects. Therefore, even warm non-flame objects may exhibit relatively high infrared radiation, increasing the difficulty of differentiation. Thus, setting a higher temperature difference threshold (such as 30K) helps to more accurately distinguish true fire points from high-temperature points caused by sunlight. In contrast, at night, without the interference of solar radiation, a lower brightness temperature difference (such as 15K) is sufficient to distinguish flames from other heat sources. Through this method, the number of false alarms can be effectively reduced, and the accuracy and reliability of fire point detection can be improved. Correctly identifying fire points is not only related to the efficiency of the fire monitoring and warning system but also directly affects the timeliness and effectiveness of fire emergency response and resource allocation.

[0084] It should be noted that those skilled in the art can set the magnitudes of the first brightness temperature difference threshold and the second brightness temperature difference threshold according to actual needs, and the present invention does not make any limitations in this regard.

[0085] In a possible implementation, the first brightness temperature difference threshold is 30K, and the second brightness temperature difference threshold is 15K.

[0086] Here, K represents the Kelvin temperature unit. This relatively high threshold of 30K is usually used for fire point identification under daytime conditions. During the day, due to sunlight irradiation, the surface temperature of the earth is generally high, which may lead to an increase in radiative brightness temperature, thus increasing the possibility of misjudgment. Setting a relatively high brightness temperature difference threshold helps to distinguish real flames from high-temperature phenomena caused by direct sunlight or other heat sources. This relatively low threshold of 15K is commonly used for fire point identification at night. At night, due to the lack of solar radiation, the temperature of the ground and the environment is usually low. Therefore, the difference in radiative brightness temperature between the flame and the background does not need to be very large to be clearly distinguishable. Thus, a lower brightness temperature difference threshold helps to effectively identify fire points at night while avoiding false negatives caused by overly strict conditions. Through such settings, the identification strategy can be flexibly adjusted according to different environmental conditions (day-night variation), optimizing the accuracy and reliability of fire point identification. This method of adjusting the threshold based on time and environmental conditions helps to provide more accurate fire point detection results in different monitoring scenarios.

[0087] S8: Combine the fast conversion parameters to perform a secondary screening of the cloud and water body regions for the initially screened fire points, and retain the target fire points.

[0088] It should be noted that by using the fast conversion parameter to perform a secondary screening of the cloud and water body regions for the initially screened fire points, the accuracy of fire point recognition is greatly improved. This step can effectively avoid misjudgment caused by the high reflectivity or other characteristics of these regions by identifying and excluding the influence of cloud and water body covered areas, further reducing the false alarm rate and enhancing the practicability and reliability of the system.

[0089] In one possible implementation, S8 specifically includes:

[0090] S801: Determine the pixel points of the cloud and water body regions on the satellite image.

[0091] S802: Establish a buffer region discrimination formula for the pixel points of the cloud and water body regions. The buffer region discrimination formula is specifically:

[0092]

[0093] where m represents the number of pixel unit lengths spaced in the x-axis direction from the pixel points of the cloud and water body regions, n represents the number of pixel unit lengths spaced in the y-axis direction from the pixel points of the cloud and water body regions, and km represents the distance unit in kilometers.

[0094] S803: Determine the buffer region of the pixel points of the cloud and water body regions according to the buffer region discrimination formula.

[0095] S804: Remove the initially screened fire points located in the buffer region to obtain the target fire points.

[0096] Specifically, by setting up a buffer zone for the cloud and water body regions to exclude possible misidentified fire points, the accuracy of fire point detection is greatly improved. In satellite images, the spectral reflection characteristics of clouds and water bodies may be similar to those of fires, which easily leads to false alarms. By creating a buffer zone and excluding the initially screened fire points within these regions, this method effectively avoids misidentification and ensures that only real fire points are identified and reported, thus increasing the reliability of the overall fire point monitoring system.

[0097] The beneficial effects brought by the technical solution provided by the embodiments of the present invention at least include:

[0098] In the present invention, first, by combining satellite attitude and orbit data, fast conversion parameters for converting the coordinates of each pixel point in the satellite image into pixel point coordinates in the pixel coordinate system are established. Furthermore, irrelevant interference filtering at the pixel point level can be effectively and quickly carried out. After initially determining the initial fire points through radiation brightness temperature, a first screening is performed using the radiation brightness temperature difference of the satellite at different radiation wavelengths to eliminate false fire points caused by warm backgrounds. Then, the cloud and water body regions are determined using the obtained coordinate conversion parameters, and the initial fire points after the first screening belonging to the cloud and water body regions are further removed to obtain more accurate fire points, further reducing the false positive rate of fire points and increasing the practicality of fire point recognition based on satellite images.

[0099] Refer to the appended Figure 2 drawings, which show a schematic structural diagram of a fire point recognition system based on satellite images provided by the present invention.

[0100] The present invention also provides a fire point recognition system 20 based on satellite images, which is applied to the above-mentioned fire point recognition method based on satellite images and includes:

[0101] A processor 201.

[0102] A memory 202, on which computer-readable instructions are stored. When the computer-readable instructions are executed by the processor 201, the fire point recognition method based on satellite images as in the method embodiment is implemented.

[0103] The fire point recognition system 20 based on satellite images provided by the present invention can execute the above-mentioned fire point recognition method based on satellite images and achieve the same or similar technical effects. To avoid repetition, the present invention will not elaborate further.

[0104] The beneficial effects brought by the technical solution provided in the embodiment of the present invention at least include:

[0105] In the present invention, first, by combining satellite attitude and orbit data, fast conversion parameters for converting the coordinates of each pixel point in the satellite image into pixel point coordinates in the pixel coordinate system are established. Furthermore, irrelevant interference filtering at the pixel point level can be effectively and quickly carried out. After initially determining the initial fire points through radiation brightness temperature, a first screening is performed using the radiation brightness temperature difference of the satellite at different radiation wavelengths to eliminate false fire points caused by warm backgrounds. Then, the cloud and water body regions are determined using the obtained coordinate conversion parameters, and the initial fire points after the first screening belonging to the cloud and water body regions are further removed to obtain more accurate fire points, further reducing the false positive rate of fire points and increasing the practicality of fire point recognition based on satellite images.

[0106] It should be understood that the processor in the embodiments of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0107] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM) or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0108] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more collections of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0109] It should be understood that the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. Additionally, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be specifically understood by referring to the context.

[0110] In the present invention, "at least one" means one or more, and "a plurality" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0111] It should be understood that in various embodiments of the present invention, the magnitudes of the sequence numbers of the above processes do not imply the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0112] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0113] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described devices, apparatuses, and units can refer to the corresponding processes in the foregoing method embodiments and will not be described herein again.

[0114] In several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0115] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0116] In addition, the functional units in each embodiment of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0117] When the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical discs that can store program codes.

[0118] An embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, characterized in that when the program is executed by a processor, it implements the method for identifying fire points based on satellite images as described in the method embodiment.

[0119] The computer-readable storage medium provided by the present invention can implement the steps and effects of the method for identifying fire points based on satellite images in the above method embodiment. To avoid repetition, the present invention will not elaborate further.

[0120] The beneficial effects brought by the technical solution provided by the embodiments of the present invention at least include:

[0121] In the present invention, first, in combination with satellite attitude and orbit data, fast conversion parameters for converting the coordinates of each pixel point in the satellite image into the coordinates of pixel points in the pixel coordinate system are established. Furthermore, irrelevant interference at the pixel point level can be effectively and quickly filtered out. After initially determining the initial fire points through the radiance temperature, a first screening is performed using the radiance temperature difference of the satellite at different radiation wavelengths to eliminate false fire points caused by warm backgrounds. Then, the cloud and water body regions are determined using the obtained coordinate conversion parameters, and the initial fire points after the first screening belonging to the cloud and water body regions are further removed to obtain more accurate fire points, further reducing the false alarm rate of fire points and increasing the practicality of fire point identification based on satellite images.

[0122] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

[0123] The following points need to be explained:

[0124] (1) The accompanying drawings of the embodiments of the present invention only relate to the structures involved in the embodiments of the present invention, and other structures can refer to the general design.

[0125] (2) For clarity, in the accompanying drawings used to describe the embodiments of the present invention, the thickness of layers or regions is enlarged or reduced, that is, these drawings are not drawn to actual scale. It can be understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, the element can be "directly" on or under the other element or there can be intervening elements.

[0126] (3) Without conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other to obtain new embodiments.

[0127] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for identifying fire points based on satellite images, characterized in that: include: S1: Acquire satellite attitude and orbit data corresponding to the acquisition of the satellite image, wherein the satellite attitude and orbit data include satellite speed at the exposure time, satellite position at the exposure time, and satellite attitude angle at the exposure time; S2: In combination with the satellite attitude and orbit data, establish fast conversion parameters for converting the coordinates of each pixel point in the satellite image into the coordinates of the pixel point in the pixel coordinate system, wherein the fast conversion parameters include the coordinates of the center point of the satellite image in the pixel coordinate system and the length of a single pixel point of the satellite image in each coordinate axis direction in the image coordinate system; S3: using the fast conversion parameters to convert each image coordinate of the satellite image into a world coordinate in a geocentric coordinate system; S4: Acquire the longitude and latitude of each world coordinate of the satellite image in the geocentric coordinate system according to the world coordinate; S5: converting the brightness value of the pixel to be detected in the satellite image into a radiation brightness temperature; S6: When the radiation brightness temperature is greater than the radiation brightness temperature threshold set according to the longitude and latitude, the pixel point to be detected is determined as an initial fire point; S7: Screening the initial fire points according to the radiation brightness temperature difference of the pixel points to be detected at different radiation wavelengths; S8: performing a secondary screening of the cloud and water area on the initial fire points after the primary screening in combination with the rapid conversion parameters, and retaining the target fire points; Wherein, the S2 specifically includes: S201: Determine the coordinates of four corner points and the center point in the satellite image; S202: Acquire the corner point coordinates and the center point coordinates in the world coordinate system corresponding to the corner point world coordinates and the center point world coordinates according to the satellite attitude and orbit data; S203: Substituting the obtained world coordinates of the corner point and the world coordinates of the center point into the association equation between the world coordinate system and the image coordinate system to solve the fast conversion parameter. The association equation is specifically: Wherein, (X, Y) represents the world coordinates, I and J represent the pixel row number and pixel column number of the satellite image, respectively, (x0, y0) represents the world coordinates of the center point, w and h represent the width and height of the satellite image, respectively, and dx and dy represent the length of a single pixel point of the satellite image in the X-axis direction and the Y-axis direction in the image coordinate system, respectively; Wherein, the S3 specifically includes: S301: Using the fast conversion parameters to convert the image coordinates into pixel coordinates in a pixel coordinate system : Wherein, (x, y) represents the image coordinates; S302: Calculate the sensor coordinates of the satellite image in the sensor coordinate system by combining the internal orientation element matrix of the satellite infrared payload : Among them, f λ represents the focal length of the infrared camera in the wavelength band, (x'0, y'0) represents the coordinates of the principal point in the phase plane; S303: Calculate the orbital coordinates of the image coordinates in the orbital coordinate system in combination with the attitude equivalent matrix of the satellite at the exposure time, and convert the orbital coordinates into world coordinates; S304: Calculate the world coordinates of the image coordinates according to the conversion matrix between the orbital coordinate system and the geocentric coordinate system: in, Represents the world coordinates of the image coordinates, R T represents the transformation matrix; Wherein, the S8 specifically includes: S801: Determine pixel points in the cloud and water area on the satellite image; S802: Establishing a buffer region discrimination formula for the pixel points in the cloud and water region. The buffer region discrimination formula is specifically: Wherein, m represents the number of pixel unit lengths spaced from the pixel point of the cloud and water body region in the x-axis direction, n represents the number of pixel unit lengths spaced from the pixel point of the cloud and water body region in the y-axis direction, and km represents the distance unit in kilometers; S803: Determine the buffer area of ​​the pixel points in the cloud and water area according to the buffer area discrimination formula; S804: removing the initial fire points located in the buffer area after a screening, and obtaining the target fire points.

2. The method for identifying fire points based on satellite images according to claim 1, characterized in that: The world coordinates for obtaining the latitude and longitude of each world coordinate of the satellite image in the geocentric coordinate system are specifically: Among them, α represents longitude and β represents latitude.

3. The method for identifying fire points based on satellite images according to claim 1, characterized in that: The radiation brightness temperature is specifically: Wherein, T represents the radiation brightness temperature, b represents the Wien shift constant, λ represents the radiation wavelength, ln represents the natural logarithm, L(λ) represents the radiant brightness L at a given radiation wavelength of λ, h represents the Planck constant, c represents the speed of light, k represents the Boltzmann constant, G represents the calibration slope, B represents the calibration intercept, DN represents the brightness value of the pixel to be detected, and e represents the base of the natural logarithm.

4. The method for identifying fire points based on satellite images according to claim 1, characterized in that: The S7 specifically includes: S701: Obtaining the radiation brightness temperature difference of the pixel to be detected in two bands different from the radiation wavelength; S702: Determine whether the current time is day or night. If the current time is day, proceed to S703; otherwise, proceed to S704; S703: When the radiation brightness temperature difference is greater than a first brightness temperature difference threshold, retaining the initial fire point corresponding to the pixel to be detected; S704: When the radiation brightness temperature difference is greater than a second brightness temperature difference threshold, retain the initial fire point corresponding to the pixel to be detected.

5. The method for identifying fire points based on satellite images according to claim 4, characterized in that: The first brightness temperature difference threshold is 30K, and the second brightness temperature difference threshold is 15K.

6. A fire point identification system based on satellite images, characterized in that: include: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the satellite image-based fire point identification method as described in any one of claims 1 to 5 is implemented.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the satellite image-based fire point identification method as described in any one of claims 1 to 5 is implemented.

Images