Satellite image framing cutting and RPC parameter generation method and device
By performing preset classification model identification and RPC parameter calculation on the images after cropping of satellite images, geometric correction is performed for different application scenarios, the problem of complex and inaccurate calculation of polynomial coefficients in the prior art is solved, and data processing efficiency is improved Accuracy.
Patent Information
- Application Number
- CN202410941192.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-15
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2044-07-15
AI Technical Summary
The existing satellite image cropping methods cannot accurately calibrate geometrically for different application scenarios, resulting in complex and inaccurate calculation of polynomial coefficients, which affects data processing efficiency.
By performing preset classification model identification of the cropped images, the features of the elements to be removed are determined, and RPC parameters are calculated based on the application scenario for geometric correction, including specific processing of natural environment, urban construction and agricultural land use scenarios.
It improves data processing efficiency, ensures the accuracy and consistency of the corrected images, and provides customized image data processing solutions for different application scenarios.
Smart Images

Figure CN118918306A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of satellite image cropping, and in particular to a satellite image framing cropping and RPC parameter generation method and device. Background Art
[0002] When dealing with satellite images with actual usage scenarios, existing satellite image cropping methods are unable to determine the degree of correlation between the feature characteristics in the actual application scenario and the cropped image, thus requiring the retention of a large number of redundant feature characteristics, which in turn reduces data processing efficiency.
[0003] When geometrically calibrating framed images, polynomial coefficients (Rational Polynomial Coefficients, RPC) are usually used to achieve it. However, if the effect of terrain on image geometry is taken into account, the calculation process of the polynomial coefficients is usually particularly complicated. When facing each cropped image after satellite image cropping, if different cropped images will be used in different application scenarios, it is usually impossible to calculate the polynomial coefficients separately for different application scenarios, so that the final polynomial coefficients do not take into account different application scenarios, that is, the polynomial coefficients used for geometric calibration are not accurate enough.
[0004] Currently, there is no technical solution that can solve the above technical problems, and there is no method and device for satellite image segmentation and cropping and RPC parameter generation. Summary of the invention
[0005] The present invention provides a satellite image framing and cropping and RPC parameter generation method and device, which performs redundant feature elimination and RPC parameter calculation for different application scenarios corresponding to different cropped images, thereby improving data processing efficiency and making the corrected image more accurate.
[0006] In a first aspect, the present invention provides a satellite image framing and RPC parameter generation method, comprising:
[0007] Crop the original satellite image in sections to obtain all cropped images;
[0008] For each cropped image, input the cropped image into a preset classification model to obtain an image recognition result output by the preset classification model;
[0009] Determine the features of the elements to be removed according to the application scenarios of the cropped images, remove the image recognition results having the features of the elements to be removed from the cropped images, and obtain the removed images, wherein the application scenarios include natural environment scenes, urban construction scenes, and agriculture and land use scenes;
[0010] According to the application scenario, calculating the RPC parameters corresponding to the removed image, performing geometric correction on the removed image using the RPC parameters, and determining a corrected image;
[0011] The preset classification model is determined after training based on all image samples and the marking labels corresponding to different element features in each image sample, and the marking labels include lakes, rivers, reservoirs, forests, grasslands, farmlands, houses, roads, bridges, bare soil, rocks and deserts.
[0012] According to the satellite image framing and RPC parameter generation method provided by the present invention, the feature of the element to be removed is determined according to the application scenario of the cropped image, including:
[0013] When the application scenario is a natural environment scenario, determining the features of the elements to be removed to be houses, roads and bridges;
[0014] When the application scenario is an urban construction scenario, the features of the elements to be removed are determined to be lakes, rivers, reservoirs, forests, grasslands, and farmlands;
[0015] When the application scenario is an agriculture and land use scenario, the features of the elements to be removed are determined to be houses, roads, bridges, bare soil, rocks and deserts.
[0016] According to the satellite image framing and RPC parameter generation method provided by the present invention, when the application scenario is a natural environment scenario, the RPC parameters corresponding to the removed image are calculated according to the application scenario, including:
[0017] Registering the original digital elevation model data according to the geographic coordinates and longitude and latitude information of the cropped image to obtain the target digital elevation model data corresponding to the cropped image;
[0018] Performing terrain correction on the cropped image using the target digital elevation model data to obtain a corrected image;
[0019] A first RPC model is constructed according to the platform position, platform posture and pixel size corresponding to the corrected image, and the RPC parameters corresponding to the eliminated image are solved based on the first RPC model.
[0020] According to the satellite image framing and RPC parameter generation method provided by the present invention, the first RPC model is constructed according to the platform position, platform posture and pixel size corresponding to the corrected image, including:
[0021]
[0022] Among them, (X im, Y im , Z im ) is the pixel coordinate of the platform position in the image coordinate system considering the terrain, (X, Y) is the geographic coordinate in the geographic coordinate system, (Roll, Pitch, Yaw) is the platform posture, (Sx, Sy) is the pixel size, and function f and function g are polynomial functions.
[0023] According to the satellite image framing and RPC parameter generation method provided by the present invention, solving the RPC parameters corresponding to the removed image based on the first RPC model includes:
[0024] All first polynomial coefficients in function f are solved by least square method, all second polynomial coefficients in function g are solved, and all first polynomial coefficients and all second polynomial coefficients are determined as RPC parameters corresponding to the removed image.
[0025] According to the satellite image framing and RPC parameter generation method provided by the present invention, when the application scenario is an urban construction scenario, the RPC parameters corresponding to the removed image are calculated according to the application scenario, including: constructing a second RPC model according to the platform position, platform posture, pixel size, building edge information and urban feature information corresponding to the removed image, and solving the RPC parameters corresponding to the removed image based on the second RPC model;
[0026] The second RPC model is constructed according to the platform position, platform posture, pixel size, building edge information and city feature information corresponding to the removed image, including:
[0027]
[0028] Among them, (X im , Y im ) is the pixel coordinate of the platform position in the image coordinate system without considering the terrain, (X, Y) is the geographic coordinate in the geographic coordinate system, (Roll, Pitch, Yaw) is the platform posture, (Sx, Sy) is the pixel size, BE is the building edge information Building_Edges, UF is the urban feature information Urban_Features, and function f and function g are polynomial functions.
[0029] According to the satellite image framing and RPC parameter generation method provided by the present invention, when the application scenario is an agricultural and land use scenario, the RPC parameters corresponding to the removed image are calculated according to the application scenario, including: constructing a third RPC model according to the platform position, platform attitude, pixel size, vegetation index information and farmland feature information corresponding to the removed image, and solving the RPC parameters corresponding to the removed image based on the third RPC model;
[0030] The third RPC model is constructed according to the platform position, platform posture, pixel size, vegetation index information and farmland feature information corresponding to the removed image, including:
[0031]
[0032] Among them, (X im , Y im ) is the pixel coordinate of the platform position in the image coordinate system without considering the terrain, (X, Y) is the geographic coordinate in the geographic coordinate system, (Roll, Pitch, Yaw) is the platform posture, (Sx, Sy) is the pixel size, VI is the vegetation index information Vegetation_Index, FF is the farmland feature information Farmland_Features, and function f and function g are polynomial functions.
[0033] According to the satellite image framing and RPC parameter generation method provided by the present invention, after determining the corrected image, the method further includes:
[0034] Traversing all original satellite images, determining a corrected image and RPC parameters corresponding to each of the original satellite images;
[0035] All corrected images and the RPC parameters corresponding to each corrected image are output to a preset storage unit to implement geometric information processing of different corrected images according to different application scenarios.
[0036] According to the satellite image framing and RPC parameter generation method provided by the present invention, framing and framing the original satellite image to obtain all the cropped images includes:
[0037] Using GIS software to load the original satellite image, and determining the cropping range from the original satellite image according to the geographic coordinates and longitude and latitude information;
[0038] Crop the original satellite image in the cropping range in sections to obtain all cropped images;
[0039] The geographic coordinates and the latitude and longitude information are determined after a preset geographic entity is superimposed as a layer on the original satellite image.
[0040] In a second aspect, a satellite image framing and RPC parameter generation device is provided, comprising:
[0041] An acquisition unit is used to crop the original satellite image in sections and acquire all cropped images;
[0042] An input unit, for inputting each cropped image into a preset classification model to obtain an image recognition result output by the preset classification model;
[0043] A removal unit is used to determine the features of the elements to be removed according to the application scenario of the cropped image, and remove the image recognition results having the features of the elements to be removed from the cropped image to obtain the removed image, wherein the application scenario includes a natural environment scene, an urban construction scene, and an agriculture and land use scene;
[0044] A determination unit, configured to calculate the RPC parameters corresponding to the eliminated image according to the application scenario, and to perform geometric correction on the eliminated image using the RPC parameters to determine a corrected image;
[0045] The preset classification model is determined after training based on all image samples and the marking labels corresponding to different element features in each image sample, and the marking labels include lakes, rivers, reservoirs, forests, grasslands, farmlands, houses, roads, bridges, bare soil, rocks and deserts.
[0046] The present invention obtains accurate recognition results of different element features by inputting the cropped image into a preset classification model, aiming to crop and identify elements in specific scenes from the original satellite image, and to eliminate and geometrically correct the image to obtain image data that meets the needs of specific application scenarios, and then calculate the RPC parameters corresponding to the eliminated image in combination with the application scenario, perform geometric correction on the image, and then more accurately convert the image pixel coordinates into geographic coordinates to ensure the accuracy and consistency of the image data in space. The present invention can flexibly determine the characteristics of the eliminated elements and perform geometric correction according to the needs of different application scenarios, and provide customized image data processing solutions for different fields such as natural environment, urban construction and agricultural land use. BRIEF DESCRIPTION OF THE DRAWINGS
[0047] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0048] Figure 1It is one of the flow charts of the satellite image framing and RPC parameter generation method provided by the present invention;
[0049] Figure 2 This is the second flow chart of the satellite image framing and RPC parameter generation method provided by the present invention;
[0050] Figure 3 It is a structural schematic diagram of a satellite image framing and RPC parameter generating device provided by the present invention;
[0051] Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION
[0052] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0053] Figure 1 It is one of the flow charts of the satellite image framing and cropping and RPC parameter generation method provided by the present invention, and the satellite image framing and cropping and RPC parameter generation method comprises:
[0054] Step 101, cropping the original satellite image in sections to obtain all cropped images;
[0055] Step 102: for each cropped image, input the cropped image into a preset classification model to obtain an image recognition result output by the preset classification model;
[0056] Step 103: determining the features of the elements to be removed according to the application scenarios of the cropped images, removing the image recognition results having the features of the elements to be removed from the cropped images, and obtaining the removed images, wherein the application scenarios include natural environment scenes, urban construction scenes, and agriculture and land use scenes;
[0057] Step 104: Calculate the RPC parameters corresponding to the removed image according to the application scenario, perform geometric correction on the removed image using the RPC parameters, and determine a corrected image;
[0058] The preset classification model is determined after training based on all image samples and the marking labels corresponding to different element features in each image sample, and the marking labels include lakes, rivers, reservoirs, forests, grasslands, farmlands, houses, roads, bridges, bare soil, rocks and deserts.
[0059] In step 101, the original satellite image is cropped in sections to obtain all cropped images, including: using GIS software to load the original satellite image, and determining a cropping range from the original satellite image according to geographic coordinates and longitude and latitude information; the original satellite image is cropped in sections within the cropping range to obtain all cropped images; the geographic coordinates and the longitude and latitude information are determined after a preset geographic entity is superimposed as a layer on the original satellite image.
[0060] Optionally, the present invention uses a geographic information system (GIS) tool to load raw satellite images and geographic information data, determines the cropping range by drawing vector boundaries or polygonal ranges, and accurately determines the boundaries of the cropping range based on geographic coordinates and longitude and latitude information to ensure that the cropped image completely corresponds to the geographic entity. Existing geographic data, topographic maps or satellite images can also be referenced to assist in determining the cropping range to ensure that the cropped image matches the surrounding environment.
[0061] By using GIS software or professional remote sensing image processing software, you can use the automatic cropping function to remove excess pixel data and reduce redundant information; apply image processing algorithms, such as edge detection and feature extraction, to identify and remove unnecessary data and retain key information; carefully select the cropping range according to project requirements and analysis purposes, remove unnecessary areas and information, and reduce data redundancy.
[0062] Optionally, the present invention can also perform multi-threaded cropping on the original satellite image to improve processing efficiency, adopt parallel processing technology, process multiple images at the same time, speed up the cropping speed, and while increasing the cropping speed, ensure that the cropped image completely corresponds to the actual geographical location, avoid information deviation and inconsistency, remove redundant information, reduce data volume, and improve data processing and storage efficiency.
[0063] In step 102, the present invention determines the preset classification model after training based on all image samples and the marking labels corresponding to different element features in each image sample, wherein the different element features are marked in the form of manual marking, specifically, the marking labels include lakes, rivers, reservoirs, forests, grasslands, farmlands, houses, roads, bridges, bare soil, rocks and deserts, so that after the cropped image is input into the preset classification model, the image recognition result output by the preset classification model is obtained.
[0064] Specifically, the present invention can utilize a support vector machine (SVM) to classify remote sensing images through a preset classification model to determine an image recognition result, thereby removing corresponding redundant information.
[0065] In step 103, the features of the elements to be removed are determined according to the application scenario of the cropped image, including: when the application scenario is a natural environment scene, the features of the elements to be removed are determined to be houses, roads and bridges; when the application scenario is an urban construction scene, the features of the elements to be removed are determined to be lakes, rivers, reservoirs, forests, grasslands and farmlands; when the application scenario is an agriculture and land use scene, the features of the elements to be removed are determined to be houses, roads, bridges, bare soil, rocks and deserts.
[0066] In an optional embodiment, if the application scenario corresponding to the cropped image is a natural environment scene, and the image recognition result output by the preset classification model includes houses and roads, the image recognition result with the characteristics of the elements to be eliminated is removed from the cropped image, that is, the houses and roads are eliminated from the cropped image to obtain a eliminated image; and in another optional embodiment, the application scenario corresponding to the cropped image is an urban construction scene, and the image recognition result output by the preset classification model includes grassland and farmland, then the image recognition result with the characteristics of the elements to be eliminated is removed from the cropped image, that is, the grassland and farmland are eliminated from the cropped image to obtain a eliminated image; and in another optional embodiment, the application scenario corresponding to the cropped image is an agriculture and land use scene, and the image recognition result output by the preset classification model includes bridges, bare soil and deserts, then the image recognition result with the characteristics of the elements to be eliminated is removed from the cropped image, that is, the bridges, bare soil and deserts are eliminated from the cropped image to obtain a eliminated image,
[0067] In step 104, the present invention again combines the application scenario to calculate the RPC parameters corresponding to the eliminated image, that is, for different application scenarios, different methods are used to calculate the eliminated image to obtain more accurate RPC parameters. The present invention uses a terrain-independent RPC parameter conversion method: this method does not consider the impact of terrain on image geometry, but focuses more on the accuracy of geometric correction. According to the RPC parameters, the eliminated image is geometrically corrected, and the geometric shape of the eliminated image is adjusted to make it conform to the geographic coordinate system and geographic coordinate information.
[0068] Optionally, the geolocation accuracy of the image is further adjusted based on the corrected image and RPC parameters to ensure the accuracy of the image's geographical location. The geolocation accuracy of the image can be further improved by aligning it with a geographic information system or other geographic data. After completing geometric correction and geolocation, the present invention can also verify the corrected image to ensure the accuracy of the geometric shape and geographic location.
[0069] Optionally, after determining the corrected image, the method further includes:
[0070] Traversing all original satellite images, determining a corrected image and RPC parameters corresponding to each of the original satellite images;
[0071] All corrected images and the RPC parameters corresponding to each corrected image are output to a preset storage unit to implement geometric information processing of different corrected images according to different application scenarios.
[0072] Optionally, the present invention traverses all original satellite images, uses the above steps to determine the corrected images and RPC parameters corresponding to each of the original satellite images, and then outputs all corrected images after geometric correction and geolocation processing and the RPC parameters corresponding to each corrected image. This information will be used for subsequent geographic information processing and application, and can be pre-stored in a preset storage unit for subsequent call at any time.
[0073] The present invention obtains accurate recognition results of different element features by inputting the cropped image into a preset classification model, aiming to crop and identify elements in specific scenes from the original satellite image, and to eliminate and geometrically correct the image to obtain image data that meets the needs of specific application scenarios. The image is combined with the application scenario again to calculate the RPC parameters corresponding to the eliminated image, perform geometric correction on the image, and then more accurately convert the image pixel coordinates into geographic coordinates to ensure the spatial accuracy and consistency of the image data. The present invention can flexibly determine the characteristics of the eliminated elements and perform geometric correction according to the needs of different application scenarios, and provide customized image data processing solutions for different fields such as natural environment, urban construction and agricultural land use.
[0074] Figure 2 This is a second flow chart of the satellite image framing and RPC parameter generation method provided by the present invention. When the application scenario is a natural environment scenario, the RPC parameters corresponding to the removed image are calculated according to the application scenario, including:
[0075] Step 201: registering the original digital elevation model data according to the geographic coordinates and longitude and latitude information of the cropped image to obtain the target digital elevation model data corresponding to the cropped image;
[0076] Step 202: Perform terrain correction on the cropped image using the target digital elevation model data to obtain a corrected image;
[0077] Step 203: construct a first RPC model according to the platform position, platform posture and pixel size corresponding to the corrected image, and solve the RPC parameters corresponding to the eliminated image based on the first RPC model.
[0078] In step 201, it is necessary to obtain the geographic coordinate information of the cropped image, which usually includes the latitude and longitude coordinates of the upper left corner and the lower right corner of the image, as well as information such as the resolution of the image. The original digital elevation model data can be interpolated or resampled to have the same spatial resolution and coverage as the image. The geographic coordinate information of the cropped image is used to align the original digital elevation model data with the cropped image to ensure that the original digital elevation model data and the cropped image are in the same coordinate system and have a consistent spatial reference frame, thereby obtaining the target digital elevation model data corresponding to the cropped image.
[0079] In step 202, before calculating the RPC parameters, the natural environment scene needs to consider the influence of the terrain. The digital elevation model provides surface elevation information. The calculation of the RPC parameters needs to be combined with terrain data to ensure that the geometric shape of the image is consistent with the actual surface conditions. The present invention uses the target digital elevation model data to extract the terrain features of the image, such as terrain height, slope, slope direction and other information. These terrain features can help understand the influence of the terrain on the image pixel coordinates and geographic coordinates, and provide a basis for terrain adjustment. According to the terrain information provided by the target digital elevation model data, the cropped image can be height-corrected. By comparing the elevation information of the cropped image pixels with the target digital elevation model data, the elevation value of the image pixels is adjusted to make it more consistent with the actual surface elevation conditions, and finally the corrected image is obtained.
[0080] In step 203, constructing a first RPC model according to the platform position, platform posture and pixel size corresponding to the corrected image includes:
[0081]
[0082] Among them, (X im , Y im , Z im ) is the pixel coordinate of the platform position in the image coordinate system considering the terrain, (X, Y) is the geographic coordinate in the geographic coordinate system, (Roll, Pitch, Yaw) is the platform posture, (Sx, Sy) is the pixel size, and function f and function g are polynomial functions.
[0083] Optionally, the RPC parameters of the image can be calculated based on information such as the platform position, platform posture, and pixel size. The RPC model is a mathematical model used for geometric correction and geographic positioning, and the relationship between pixel coordinates and geographic coordinates is described by polynomial coefficients. In natural environment scenes, the influence of terrain needs to be considered in particular, so the RPC parameter calculation method based on the digital elevation model is commonly used. By combining the digital elevation data with the corrected image, the RPC parameters can be calculated more accurately.
[0084] Optionally, solving the RPC parameters corresponding to the eliminated image based on the first RPC model includes:
[0085] All first polynomial coefficients in function f are solved by least square method, all second polynomial coefficients in function g are solved, and all first polynomial coefficients and all second polynomial coefficients are determined as RPC parameters corresponding to the removed image.
[0086] Optionally, when the application scenario is an urban construction scenario, calculating the RPC parameters corresponding to the eliminated image according to the application scenario includes: constructing a second RPC model according to a platform position, platform posture, pixel size, building edge information and urban feature information corresponding to the eliminated image, and solving the RPC parameters corresponding to the eliminated image based on the second RPC model;
[0087] The second RPC model is constructed according to the platform position, platform posture, pixel size, building edge information and city feature information corresponding to the removed image, including:
[0088]
[0089] Among them, (X im , Y im ) is the pixel coordinate of the platform position in the image coordinate system without considering the terrain, (X, Y) is the geographic coordinate in the geographic coordinate system, (Roll, Pitch, Yaw) is the platform posture, (Sx, Sy) is the pixel size, BE is the building edge information Building_Edges, UF is the urban feature information Urban_Features, and function f and function g are polynomial functions.
[0090] Optionally, in urban construction scenarios, it is usually necessary to consider the influence of buildings, roads, etc. These man-made objects will affect the geometric transformation of the image, so these factors need to be considered when calculating the RPC parameters. The present invention adopts an RPC parameter calculation method based on building edge extraction, and combines urban planning, road network and urban characteristics to calculate the RPC parameters. Specifically, the present invention first uses remote sensing image processing software or computer vision algorithms to extract the edges of buildings in the image, and extract the geometric information of the buildings, including the outlines and corner points of the buildings, and then obtains urban characteristic information related to urban planning data and road network data, including urban planning maps, road network maps, building distribution maps, etc., which are combined with the building edge information to construct a second RPC model. In the urban construction scenario, the combination of building edges and urban characteristic information can more accurately calculate the RPC parameters, considering the influence of urban characteristics such as urban planning and road networks on the image.
[0091] Optionally, when the application scenario is an agriculture and land use scenario, the calculating the RPC parameters corresponding to the removed image according to the application scenario includes: constructing a third RPC model according to the platform position, platform posture, pixel size, vegetation index information and farmland feature information corresponding to the removed image, and solving the RPC parameters corresponding to the removed image based on the third RPC model;
[0092] The third RPC model is constructed according to the platform position, platform posture, pixel size, vegetation index information and farmland feature information corresponding to the removed image, including:
[0093]
[0094] Among them, (X im , Y im ) is the pixel coordinate of the platform position in the image coordinate system without considering the terrain, (X, Y) is the geographic coordinate in the geographic coordinate system, (Roll, Pitch, Yaw) is the platform posture, (Sx, Sy) is the pixel size, VI is the vegetation index information Vegetation_Index, FF is the farmland feature information Farmland_Features, and function f and function g are polynomial functions.
[0095] Optionally, in agricultural and land use scenarios, it is usually necessary to consider the influence of natural elements such as farmland and vegetation. These natural elements will affect the geometric transformation of the image. Therefore, these factors need to be considered when calculating the RPC parameters. The present invention first uses remote sensing image processing software or vegetation index calculation method to extract vegetation index in the image after elimination, such as normalized difference vegetation index (NDVI), soil adjusted vegetation index (SAVI), etc. The vegetation index can reflect the growth status of vegetation and affect the geometric transformation of the image. Then, agricultural and land use characteristic information related to farmland distribution data and land use type data is obtained. These data may include farmland distribution maps, land use type maps, vegetation coverage, etc. In agricultural and land use scenarios, combined with building edge and urban characteristic information, the RPC parameters can be calculated more accurately, considering the influence of natural elements such as farmland and vegetation on the image after elimination.
[0096] Figure 3 It is a structural schematic diagram of the satellite image framing and cropping and RPC parameter generation device provided by the present invention. The satellite image framing and cropping and RPC parameter generation device includes an acquisition unit 1, which is used to frame and crop the original satellite image to obtain all cropped images. The working principle of the acquisition unit 1 can refer to the aforementioned step 101 and will not be repeated here.
[0097] The satellite image framing and RPC parameter generation device also includes an input unit 2, which is used to input each cropped image into a preset classification model to obtain an image recognition result output by the preset classification model. The working principle of the input unit 2 can be referred to the aforementioned step 102 and will not be repeated here.
[0098] The satellite image segmentation and RPC parameter generation device also includes a removal unit 3, which is used to determine the characteristics of the elements to be removed according to the application scenario of the cropped image, and remove the image recognition results with the characteristics of the elements to be removed from the cropped image to obtain the removed image. The application scenario includes a natural environment scene, an urban construction scene, and an agriculture and land use scene. The working principle of the removal unit 3 can refer to the aforementioned step 103 and will not be repeated here.
[0099] The satellite image framing and RPC parameter generation device also includes a determination unit 4, which is used to calculate the RPC parameters corresponding to the removed image according to the application scenario, use the RPC parameters to perform geometric correction on the removed image, and determine the corrected image. The working principle of the determination unit 4 can refer to the aforementioned step 104 and will not be repeated here.
[0100] The preset classification model is determined after training based on all image samples and the marking labels corresponding to different element features in each image sample, and the marking labels include lakes, rivers, reservoirs, forests, grasslands, farmlands, houses, roads, bridges, bare soil, rocks and deserts.
[0101] The present invention obtains accurate recognition results of different element features by inputting the cropped image into a preset classification model, aiming to crop and identify elements in specific scenes from the original satellite image, and to eliminate and geometrically correct the image to obtain image data that meets the needs of specific application scenarios, and then calculate the RPC parameters corresponding to the eliminated image in combination with the application scenario, perform geometric correction on the image, and then more accurately convert the image pixel coordinates into geographic coordinates to ensure the accuracy and consistency of the image data in space. The present invention can flexibly determine the characteristics of the eliminated elements and perform geometric correction according to the needs of different application scenarios, and provide customized image data processing solutions for different fields such as natural environment, urban construction and agricultural land use.
[0102] Figure 4 Schematic diagram of the structure of the electronic device provided by the present invention. Figure 4 As shown, the electronic device may include: a processor (processor) 410, a communication interface (Communications Interface) 420, a memory (memory) 430 and a communication bus 440, wherein the processor 410, the communication interface 420, and the memory 430 communicate with each other through the communication bus 440. The processor 410 can call the logic instructions in the memory 430 to execute the satellite image framing and RPC parameter generation method, which includes: framing the original satellite image to obtain all the cropped images; for each cropped image, input the cropped image into a preset classification model to obtain the image recognition result output by the preset classification model; according to the application scenario of the cropped image, determine the characteristics of the elements to be eliminated, and eliminate the image recognition results with the characteristics of the elements to be eliminated from the cropped image to obtain the eliminated image, and the application scenario includes a natural environment scene, an urban construction scene, and an agriculture and land use scene; according to the application scenario, calculate the RPC parameters corresponding to the eliminated image, and use the RPC parameters to perform geometric correction on the eliminated image to determine the corrected image; the preset classification model is determined after training based on all image samples and the marking labels corresponding to different element features in each image sample, and the marking labels include lakes, rivers, reservoirs, forests, grasslands, farmlands, houses, roads, bridges, bare soil, rocks, and deserts.
[0103] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.
[0104] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute a satellite image framing and RPC parameter generation method provided by the above methods. The method includes: framing and framing the original satellite image to obtain all cropped images; for each cropped image, inputting the cropped image into a preset classification model to obtain an image recognition result output by the preset classification model; determining the features of the elements to be removed according to the application scenario of the cropped image, and selecting the features from the cropped image; The image recognition results having the features of the elements to be eliminated are eliminated from the cut image to obtain the eliminated image, and the application scenarios include natural environment scenes, urban construction scenes, and agriculture and land use scenes; according to the application scenarios, the RPC parameters corresponding to the eliminated image are calculated, and the RPC parameters are used to perform geometric correction on the eliminated image to determine the corrected image; the preset classification model is determined after training based on all image samples and the marking labels corresponding to the features of different elements in each image sample, and the marking labels include lakes, rivers, reservoirs, forests, grasslands, farmlands, houses, roads, bridges, bare soil, rocks and deserts.
[0105] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to execute the satellite image framing and RPC parameter generation methods provided by the above methods, the method comprising: framing and framing the original satellite image to obtain all cropped images; for each cropped image, inputting the cropped image into a preset classification model to obtain an image recognition result output by the preset classification model; determining the features of the elements to be removed according to the application scenario of the cropped image, and removing the elements to be removed from the cropped image. The image recognition result of the feature is used to obtain the eliminated image, and the application scenarios include natural environment scenes, urban construction scenes, and agriculture and land use scenes; according to the application scenarios, the RPC parameters corresponding to the eliminated image are calculated, and the RPC parameters are used to perform geometric correction on the eliminated image to determine the corrected image; the preset classification model is determined after training based on all image samples and the marking labels corresponding to different element features in each image sample, and the marking labels include lakes, rivers, reservoirs, forests, grasslands, farmlands, houses, roads, bridges, bare soil, rocks and deserts.
[0106] The device embodiments described above are merely illustrative, wherein 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 may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.
[0107] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.
[0108] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A satellite image framing and RPC parameter generation method, characterized in that: include: Crop the original satellite image in sections to obtain all cropped images; For each cropped image, input the cropped image into a preset classification model to obtain an image recognition result output by the preset classification model; Determine the features of the elements to be removed according to the application scenarios of the cropped images, remove the image recognition results having the features of the elements to be removed from the cropped images, and obtain the removed images, wherein the application scenarios include natural environment scenes, urban construction scenes, and agriculture and land use scenes; According to the application scenario, calculating the RPC parameters corresponding to the removed image, performing geometric correction on the removed image using the RPC parameters, and determining a corrected image; The preset classification model is determined after training based on all image samples and the marking labels corresponding to different element features in each image sample, and the marking labels include lakes, rivers, reservoirs, forests, grasslands, farmlands, houses, roads, bridges, bare soil, rocks and deserts.
2. The satellite image framing and RPC parameter generation method according to claim 1, characterized in that: The step of determining the features of the elements to be removed according to the application scenario of the cropped image includes: When the application scenario is a natural environment scenario, determining the features of the elements to be removed to be houses, roads and bridges; When the application scenario is an urban construction scenario, the features of the elements to be removed are determined to be lakes, rivers, reservoirs, forests, grasslands, and farmlands; When the application scenario is an agriculture and land use scenario, the features of the elements to be removed are determined to be houses, roads, bridges, bare soil, rocks and deserts.
3. The satellite image framing and RPC parameter generation method according to claim 1, characterized in that: In the case where the application scenario is a natural environment scenario, calculating the RPC parameters corresponding to the removed image according to the application scenario includes: Registering the original digital elevation model data according to the geographic coordinates and longitude and latitude information of the cropped image to obtain the target digital elevation model data corresponding to the cropped image; Performing terrain correction on the cropped image using the target digital elevation model data to obtain a corrected image; A first RPC model is constructed according to the platform position, platform posture and pixel size corresponding to the corrected image, and the RPC parameters corresponding to the eliminated image are solved based on the first RPC model.
4. The satellite image framing and RPC parameter generation method according to claim 3, characterized in that: The constructing a first RPC model according to the platform position, platform posture and pixel size corresponding to the corrected image includes: Among them, (X im , Y im , Z im ) is the pixel coordinate of the platform position in the image coordinate system considering the terrain, (X, Y) is the geographic coordinate in the geographic coordinate system, (Roll, Pitch, Yaw) is the platform posture, (Sx, Sy) is the pixel size, and function f and function g are polynomial functions.
5. The satellite image framing and RPC parameter generation method according to claim 3, characterized in that: The step of solving the RPC parameters corresponding to the eliminated image based on the first RPC model includes: All first polynomial coefficients in function f are solved by least square method, all second polynomial coefficients in function g are solved, and all first polynomial coefficients and all second polynomial coefficients are determined as RPC parameters corresponding to the removed image.
6. The satellite image framing and RPC parameter generation method according to claim 1, characterized in that: In the case where the application scenario is an urban construction scenario, the calculating the RPC parameters corresponding to the eliminated image according to the application scenario includes: constructing a second RPC model according to the platform position, platform posture, pixel size, building edge information and urban feature information corresponding to the eliminated image, and solving the RPC parameters corresponding to the eliminated image based on the second RPC model; The second RPC model is constructed according to the platform position, platform posture, pixel size, building edge information and city feature information corresponding to the removed image, including: Among them, (X im , Y im ) is the pixel coordinate of the platform position in the image coordinate system without considering the terrain, (X, Y) is the geographic coordinate in the geographic coordinate system, (Roll, Pitch, Yaw) is the platform posture, (Sx, Sy) is the pixel size, BE is the building edge information Building_Edges, UF is the urban feature information Urban_Features, and function f and function g are polynomial functions.
7. The satellite image framing and RPC parameter generation method according to claim 1, characterized in that: In the case where the application scenario is an agricultural and land use scenario, the RPC parameters corresponding to the removed image are calculated according to the application scenario, including: constructing a third RPC model according to the platform position, platform posture, pixel size, vegetation index information and farmland feature information corresponding to the removed image, and solving the RPC parameters corresponding to the removed image based on the third RPC model; The third RPC model is constructed according to the platform position, platform posture, pixel size, vegetation index information and farmland feature information corresponding to the removed image, including: Among them, (X im , Y im ) is the pixel coordinate of the platform position in the image coordinate system without considering the terrain, (X, Y) is the geographic coordinate in the geographic coordinate system, (Roll, Pitch, Yaw) is the platform posture, (Sx, sy) is the pixel size, VI is the vegetation index information Vegetation_Index, FF is the farmland feature information Farmland_Features, and function f and function g are polynomial functions.
8. The satellite image framing and RPC parameter generation method according to claim 1, characterized in that: After determining the corrected image, the method further includes: Traversing all original satellite images, determining a corrected image and RPC parameters corresponding to each of the original satellite images; All corrected images and the RPC parameters corresponding to each corrected image are output to a preset storage unit to implement geometric information processing of different corrected images according to different application scenarios.
9. The satellite image framing and RPC parameter generation method according to claim 1, characterized in that: The original satellite image is cropped in sections to obtain all cropped images, including: Using GIS software to load the original satellite image, and determining the cropping range from the original satellite image according to the geographic coordinates and longitude and latitude information; Crop the original satellite image in the cropping range in sections to obtain all cropped images; The geographic coordinates and the latitude and longitude information are determined after a preset geographic entity is superimposed as a layer on the original satellite image.
10. A satellite image framing and RPC parameter generation device, characterized in that: include: An acquisition unit is used to crop the original satellite image in sections and acquire all cropped images; An input unit, for inputting each cropped image into a preset classification model to obtain an image recognition result output by the preset classification model; A removal unit is used to determine the features of the elements to be removed according to the application scenario of the cropped image, and remove the image recognition results having the features of the elements to be removed from the cropped image to obtain the removed image, wherein the application scenario includes a natural environment scene, an urban construction scene, and an agriculture and land use scene; A determination unit, configured to calculate the RPC parameters corresponding to the eliminated image according to the application scenario, and to perform geometric correction on the eliminated image using the RPC parameters to determine a corrected image; The preset classification model is determined after training based on all image samples and the marking labels corresponding to different element features in each image sample, and the marking labels include lakes, rivers, reservoirs, forests, grasslands, farmlands, houses, roads, bridges, bare soil, rocks and deserts.
Citation Information
Patent Citations
Remote-sensing image road acquisition method combined with kernel Fisher and multi-scale extraction
CN103034863A
Farmland identification method and system, unmanned aerial vehicle applied to agriculture
CN108629289A
Farmland area pre-screening method and device based on prior information and deep learning
CN111028255A
Remote sensing image classification method, image processing equipment and computer readable storage device
CN111401467A
Multi-source remote sensing satellite image geometric semantic integrated processing method and system
CN112288650A
