Multi-source remote sensing data processing method and device, computer equipment and storage medium

Abstract

The invention relates to the technical field of remote sensing data processing, and provides a multi-source remote sensing data processing method and device, computer equipment and a storage medium. Registering the second remote sensing data based on the corrected first remote sensing data; the color information of the corrected first remote sensing data is mapped to the registered second remote sensing data, so that the registered second remote sensing data obtains the color information, and the second remote sensing data not only has the consistency of spatial positions, but also has rich color features, and the visualization effect and practicability of the data are enhanced; the second remote sensing data with the color information and the corrected first remote sensing data are fused to generate fused remote sensing data with higher information amount and better expressive force, and the overall quality of the remote sensing data is improved.

Description

Technical Field

[0001] The present application relates to the technical field of remote sensing data processing, and in particular to a multi-source remote sensing data processing method, device, computer equipment and storage medium. Background Art

[0002] With the rapid development of remote sensing technology, a variety of remote sensing data sources such as high-resolution satellite images and drone-borne laser point clouds have been widely used in power grid planning, monitoring, and operation and maintenance. These remote sensing data sources provide the power grid industry with rich spatial information and surface features, which is of great significance for improving the level of intelligence of the power grid.

[0003] In practical applications, it is often necessary to use multiple types of remote sensing data at the same time. However, due to differences in the sources of different remote sensing data, sensor characteristics, observation conditions and other factors, these data often have problems such as inconsistent spatial positions and color distortion, resulting in poor quality of the fused data. Summary of the invention

[0004] Based on this, a multi-source remote sensing data processing method, device, computer equipment and storage medium are proposed, aiming to solve the problems of spatial position inconsistency and color distortion in multi-source remote sensing data, and provide high-quality remote sensing data support for power grid planning, monitoring and operation and maintenance.

[0005] The first aspect of the present application provides a multi-source remote sensing data processing method, the method comprising:

[0006] performing correction processing on the first remote sensing data;

[0007] registering the second remote sensing data based on the corrected first remote sensing data;

[0008] Mapping the color information of the corrected first remote sensing data onto the registered second remote sensing data;

[0009] The second remote sensing data with color information is fused with the corrected first remote sensing data to obtain fused remote sensing data.

[0010] Optionally, the correction processing of the first remote sensing data includes:

[0011] Acquiring image characteristics of the first remote sensing data;

[0012] Obtain application requirements;

[0013] Selecting a target correction processing model from a plurality of preset correction processing models according to the image characteristics and the application requirements;

[0014] The first remote sensing data is corrected using the target correction processing model.

[0015] Optionally, mapping the color information of the corrected first remote sensing data to the registered second remote sensing data includes:

[0016] Acquiring lighting information when the first remote sensing data is captured;

[0017] Performing illumination compensation on the corrected first remote sensing data according to the illumination information;

[0018] According to the pre-established mapping relationship between the first remote sensing data and the second remote sensing data, the color information of the first remote sensing data after illumination compensation is mapped to the second remote sensing data after registration.

[0019] Optionally, performing illumination compensation on the corrected first remote sensing data according to the illumination information includes:

[0020] Determining the degree of influence of the illumination information on the color information of the first remote sensing data;

[0021] Determining a light compensation parameter according to the degree of influence;

[0022] Perform illumination compensation on the corrected first remote sensing data according to the illumination compensation parameter.

[0023] Optionally, fusing the second remote sensing data with the color information with the corrected first remote sensing data to obtain fused remote sensing data includes:

[0024] Divide the shooting area into multiple sub-areas;

[0025] Acquire a first precision of the corrected first remote sensing data of each sub-region;

[0026] Acquire the second precision of the second remote sensing data with color information for each sub-region;

[0027] For each sub-region, determining target remote sensing data of the sub-region according to the first accuracy and the corresponding second accuracy;

[0028] The target remote sensing data of all sub-areas are fused to obtain fused remote sensing data.

[0029] Optionally, determining the target remote sensing data of the sub-area according to the first accuracy and the corresponding second accuracy includes:

[0030] comparing the first precision with the corresponding second precision;

[0031] When the first precision is higher than the second precision, using the second remote sensing data with color information as the target remote sensing data of the sub-region;

[0032] When the first accuracy is lower than the second accuracy, the corrected first remote sensing data is used as the target remote sensing data of the sub-area.

[0033] Optionally, the method further includes:

[0034] Performing cloud recognition on the fused remote sensing data to obtain a cloud detection result;

[0035] According to the cloud detection result, the fused remote sensing data is repaired to obtain target fused remote sensing data.

[0036] A second aspect of the present application provides a multi-source remote sensing data processing device, the device comprising:

[0037] A correction module, used for performing correction processing on the first remote sensing data;

[0038] A registration module, used for registering the second remote sensing data based on the corrected first remote sensing data;

[0039] A mapping module, used for mapping the color information of the corrected first remote sensing data to the registered second remote sensing data;

[0040] The fusion module is used to fuse the second remote sensing data with the color information with the corrected first remote sensing data to obtain fused remote sensing data.

[0041] A third aspect of the present application provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the multi-source remote sensing data processing method when executing the computer program.

[0042] A fourth aspect of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the multi-source remote sensing data processing method are implemented.

[0043] This application improves the accuracy and reliability of the first remote sensing data by correcting the first remote sensing data, and provides high-quality basic data for subsequent data registration and fusion. Using the corrected first remote sensing data as a reference, the second remote sensing data is spatially registered to ensure the consistency of the two in spatial position, providing an accurate spatial basis for subsequent color information mapping and data fusion. The color information of the corrected first remote sensing data is mapped to the registered second remote sensing data, so that the registered second remote sensing data obtains color information, so that it not only has consistency in spatial position, but also has rich color features, enhancing the visualization effect and practicality of the data. The second remote sensing data with color information is fused with the corrected first remote sensing data to generate fused remote sensing data with higher information content and better expressiveness, thereby improving the overall quality of the remote sensing data. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0045] Figure 1 It is a flowchart of the multi-source remote sensing data processing method provided in an embodiment of the present application.

[0046] Figure 2 It is a functional module diagram of the multi-source remote sensing data processing device provided in an embodiment of the present application.

[0047] Figure 3 It is a schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0049] Figure 1 The present invention provides a flowchart of a multi-source remote sensing data processing method according to an embodiment of the present invention. The multi-source remote sensing data processing method includes the following steps.

[0050] S101, performing correction processing on the first remote sensing data.

[0051] Multi-source remote sensing data refers to a variety of remote sensing data of the same area obtained through a variety of different sensors (such as optical, thermal infrared, microwave, etc.) and different platforms (such as satellites, aircraft, drones, etc.), including multi-phase, multi-spectral, multi-sensor, multi-platform and multi-resolution data. Multi-source remote sensing data has information complementarity and can provide more comprehensive and accurate surface information. The first remote sensing data of the embodiment of the present application is described by taking the satellite remote sensing image data obtained by the sensor on the satellite as an example.

[0052] The original remote sensing image data obtained from the satellite may have certain errors and distortions due to atmospheric interference, sensor errors, earth rotation and other factors. Therefore, in order to eliminate errors and distortions and improve the quality and availability of images, it is necessary to correct the first remote sensing data. The corrected first remote sensing data has accurate geographic coordinates and true color information, which is helpful for subsequent information extraction and data analysis.

[0053] In an optional implementation, the correction processing of the first remote sensing data includes:

[0054] Acquiring image characteristics of the first remote sensing data;

[0055] Obtain application requirements;

[0056] Selecting a target correction processing model from a plurality of preset correction processing models according to the image characteristics and the application requirements;

[0057] The first remote sensing data is corrected using the target correction processing model.

[0058] The image characteristics of the first remote sensing data may include, but are not limited to: image resolution, spectral range, sensor type, shooting time, shooting angle, and noise level in the image.

[0059] Application requirements refer to the specific application scenarios in which the corrected first remote sensing data will be used. Different application scenarios have different requirements for the accuracy, resolution, color reproduction, etc. of image data. For example, if the image data will be used for urban planning, the requirements for image resolution and color reproduction will be higher; if it is only used for rough terrain analysis, the requirements for image accuracy may be relatively low.

[0060] A database table is stored locally in the computer device, and the database table records the correction processing model identifiers corresponding to different image characteristics and different application requirements. For the same image characteristic, if the application requirements are different, the correction processing model identifier will be different. For the same application requirement, if the image characteristics are different, the correction processing model identifier will be different. The correction processing model identifier is used to uniquely identify the correction processing model. After obtaining the image characteristics and application requirements, the most appropriate correction processing model can be selected from a plurality of pre-set correction processing models according to the image characteristics and application requirements to perform correction processing on the original first remote sensing data. The correction processing model may include an atmospheric correction model, a radiation correction model, a geometric correction model, etc. Different correction models correspond to different image characteristics and application requirements.

[0061] For example, if there is a large amount of cloud and fog interference in the first remote sensing data, an atmospheric correction model with strong cloud and fog removal capabilities can be selected; if the color distortion of the first remote sensing data is relatively serious, a radiation correction model that can accurately restore the color can be selected.

[0062] The above optional implementation method can effectively improve the quality of remote sensing data by selecting a suitable correction processing model based on image characteristics and application requirements; automatically selecting a suitable correction processing model based on image characteristics and application requirements reduces the time cost of manually selecting and adjusting correction parameters, making data processing more automated and intelligent, and improving processing efficiency.

[0063] S102: registering the second remote sensing data based on the corrected first remote sensing data.

[0064] The corrected first remote sensing data refers to remote sensing data that has been corrected to eliminate errors and distortions and has accurate geographic coordinates and true color information, that is, first type of remote sensing data (such as satellite image data).

[0065] The second remote sensing data is remote sensing data of a different source or type from the first remote sensing data, such as laser point cloud data, drone image data, etc.

[0066] Registering the second remote sensing data based on the corrected first remote sensing data refers to aligning the first remote sensing data and the second remote sensing data in space so that the first remote sensing data and the second remote sensing data have consistent geographic coordinates and spatial reference systems. Registration can eliminate spatial dislocations and errors between different remote sensing data and improve the overall accuracy and availability of the data. The registered second remote sensing data can be effectively fused with the corrected first remote sensing data to form a more complete and accurate surface spatial data set.

[0067] Based on the corrected first remote sensing data, the process of registering the second remote sensing data can be: extracting stable feature points or feature lines from the corrected first remote sensing data, and these feature points or feature lines should have clear geographical significance, such as building corners, road intersections, etc. At the same time, extracting corresponding feature points or feature lines from the second remote sensing data. Using a feature matching algorithm, match the feature points or feature lines in the first remote sensing data with the feature points or feature lines in the second remote sensing data to establish a corresponding relationship between the two. According to the matched feature points or feature lines, solve the spatial transformation model from the second remote sensing data to the first remote sensing data, such as affine transformation, projection transformation, etc. The solved spatial transformation model is applied to the second remote sensing data to align it with the corrected first remote sensing data in space.

[0068] In the above implementation, since the corrected first remote sensing data eliminates errors and distortions and has higher quality, the second remote sensing data is registered based on the corrected first remote sensing data, which can improve the accuracy and reliability of the registration. In addition, the corrected first remote sensing data has stable feature points or feature lines, which can be used to establish a corresponding relationship with the second remote sensing data, thereby simplifying the registration process and reducing the amount of calculation, thereby improving the registration efficiency.

[0069] S103, mapping the color information of the corrected first remote sensing data to the registered second remote sensing data.

[0070] Since the first remote sensing data has been corrected and the color information has been preserved, its color information has high accuracy and reliability. By mapping the color information of the corrected first remote sensing data to the registered second remote sensing data, high-quality color information is transferred from the corrected first remote sensing data to the registered second remote sensing data, thereby compensating for the deficiency of the second remote sensing data in color information and enhancing the visual expression and information extraction capabilities of the registered second remote sensing data.

[0071] The color information of the corrected first remote sensing data can be converted from the original color space (such as RGB) to a color space (such as HSV, Lab, etc.) that is more suitable for processing and analysis. In the converted color space, color features such as hue, saturation, brightness, etc. are extracted. The extracted color features are mapped to the registered second remote sensing data. Direct mapping, interpolation mapping, statistical mapping, etc. can be selected for mapping.

[0072] In an optional implementation, mapping the color information of the corrected first remote sensing data onto the registered second remote sensing data comprises:

[0073] Acquiring lighting information when the first remote sensing data is captured;

[0074] Performing illumination compensation on the corrected first remote sensing data according to the illumination information;

[0075] According to the pre-established mapping relationship between the first remote sensing data and the second remote sensing data, the color information of the first remote sensing data after illumination compensation is mapped to the second remote sensing data after registration.

[0076] Lighting information is one of the important factors that affect color accuracy in remote sensing images. Different lighting conditions will cause changes in the color distribution of the image, thus affecting subsequent image analysis and interpretation. Therefore, before mapping the color information of the first remote sensing data to the second remote sensing data, it is necessary to first obtain the lighting information when the first remote sensing data was taken.

[0077] Lighting information can be obtained from metadata of remote sensing images (such as shooting time, solar altitude angle, azimuth, etc.), meteorological data (such as cloud thickness, atmospheric transparency, etc.), and ground observation data. Metadata, meteorological data, ground observation data, etc. can provide detailed information about the sky conditions, sun position, and atmospheric conditions at the time of shooting, from which the lighting conditions of the image can be inferred. For example, the solar altitude angle and azimuth angle can be calculated based on metadata to infer the lighting conditions of the image; or meteorological data can be used to evaluate the impact of atmospheric conditions on lighting.

[0078] The purpose of illumination compensation is to adjust the color distribution of remote sensing images to eliminate or reduce the impact of lighting conditions on color accuracy. By performing illumination compensation on the corrected first remote sensing data, its color information can be closer to the actual situation, providing stronger support for subsequent color information mapping. Illumination compensation can be performed using histogram equalization, homomorphic filtering, Retinex theory, etc.

[0079] After the illumination compensation is completed, the color information of the first remote sensing data after illumination compensation can be mapped to the second remote sensing data after registration according to the pre-established mapping relationship between the first remote sensing data and the second remote sensing data. The mapping relationship between the first remote sensing data and the second remote sensing data can be established by matching based on feature points, matching based on gray values, matching based on transform domains, etc.

[0080] The above optional implementation method, by obtaining the lighting information when the first remote sensing data was taken, helps to more accurately evaluate the color deviation of the first remote sensing data, and provides a basis for subsequent lighting compensation; in addition, it can perform differentiated processing on the remote sensing data under different lighting conditions to improve the flexibility and adaptability of the overall lighting compensation. Using the acquired lighting information, the corrected first remote sensing data is subjected to lighting compensation to eliminate or reduce the impact of lighting changes on color information. Lighting compensation helps to make the color information of the first remote sensing data more consistent with the color information under standard or reference conditions, and provides more favorable conditions for subsequent color mapping. Using the pre-established mapping relationship, it can be ensured that the color information of the first remote sensing data that has undergone lighting compensation can be accurately mapped to the second remote sensing data after registration, forming a composite image with consistent color and complete information.

[0081] In an optional implementation, performing illumination compensation on the corrected first remote sensing data according to the illumination information includes:

[0082] Determining the degree of influence of the illumination information on the color information of the first remote sensing data;

[0083] Determining a light compensation parameter according to the degree of influence;

[0084] Perform illumination compensation on the corrected first remote sensing data according to the illumination compensation parameter.

[0085] Different lighting conditions will cause changes in the brightness, contrast and color distribution of the image. In order to perform effective lighting compensation, it is necessary to determine the degree of influence of the lighting information on the color information of the first remote sensing data. In specific implementation, it is necessary to extract parameters such as the solar altitude angle, azimuth, atmospheric transparency, and cloud thickness from the lighting information. These parameters can reflect the sky conditions, sun position, and atmospheric conditions at the time of shooting. Then, statistical indicators such as the brightness, contrast, and saturation of the image are calculated to evaluate the color information of the first remote sensing data. Finally, the degree of influence of the lighting information on the color information of the first remote sensing data is quantified based on the extracted parameters and the calculated statistical indicators.

[0086] In an optional implementation, the following method can be used to quantify the influence of the illumination information on the color information of the first remote sensing data:

[0087] I=w1·f1(H)+w2·f2(A)+w3·f3(T)+w4·f4(C)+w5·(L-Lmin) / (Lmax-Lmin)+w6·(C-Cmin) / (Cmax-Cmin)+w7·(S-Smin) / (Smax-Smin).

[0088] Where I is the degree of influence, H is the solar altitude, A is the solar azimuth, T is the atmospheric transparency, C is the cloud thickness, L is the image brightness, C is the image contrast, and S is the image saturation. w1, w2, ..., w7 are the weights of each parameter, and the sum of the weights of each parameter is 1. f1(H), f2(A), f3(T), f4(C) are functions that convert the solar altitude, azimuth, atmospheric transparency and cloud thickness into the degree of influence on color information. The function can be linear or nonlinear. Lmin, Lmax, Cmin, Cmax, Smin, Smax are the minimum and maximum values ​​of brightness, contrast and saturation, respectively, which are used to normalize these statistical indicators.

[0089] After determining the degree of influence of the illumination information on the color information of the first remote sensing data, the illumination compensation parameters can be determined according to the degree of influence to achieve the best illumination compensation effect. The illumination compensation parameters may include the type of filter, the number of iterations, the threshold value, and the like.

[0090] Finally, according to the illumination compensation parameters, illumination compensation is performed on the corrected first remote sensing data.

[0091] After the illumination compensation is completed, the illumination compensation results can be evaluated by comparing the image quality, color distribution, and feature point matching accuracy before and after compensation. If the evaluation results show that the compensation effect is good and no obvious distortion or error is generated, the illumination compensation is considered successful. If the evaluation results show that the compensation effect is not ideal or there are some problems, the compensation parameters need to be readjusted. Through continuous iteration and optimization, more accurate and reliable illumination compensation results can be obtained.

[0092] The above optional implementation method, by determining the degree of influence of illumination information on color information and formulating illumination compensation parameters according to the degree of influence, achieves the effect of flexibly adjusting compensation parameters according to different illumination conditions and enhances the adaptability of data. This means that no matter under what illumination conditions the remote sensing data is collected, its quality can be optimized through illumination compensation to make it more suitable for subsequent application requirements. Through illumination compensation, color distortion caused by illumination can be reduced, thereby obtaining remote sensing images that are closer to real scenes.

[0093] S104, fusing the second remote sensing data with color information with the corrected first remote sensing data to obtain fused remote sensing data.

[0094] Remote sensing data acquired by different sensors or at different times have differences in resolution, spectral characteristics and temporal characteristics. By fusing these data, we can integrate the advantages of various data to form a more comprehensive and accurate remote sensing image. For the second remote sensing data with color information and the corrected first remote sensing data, fusion can improve the spatial resolution or other related characteristics of the image while retaining the color information, thereby reflecting the surface information more comprehensively.

[0095] Different weights may be assigned to the second remote sensing data with color information and the corrected first remote sensing data, and the fused remote sensing data may be obtained by weighted averaging the second remote sensing data with color information and the corrected first remote sensing data. Other fusion algorithms may also be used to fuse the second remote sensing data with color information and the corrected first remote sensing data.

[0096] In an optional implementation manner, fusing the second remote sensing data with the color information with the corrected first remote sensing data to obtain the fused remote sensing data includes:

[0097] Divide the shooting area into multiple sub-areas;

[0098] Acquire a first precision of the corrected first remote sensing data of each sub-region;

[0099] Acquire the second precision of the second remote sensing data with color information for each sub-region;

[0100] For each sub-region, determining target remote sensing data of the sub-region according to the first accuracy and the corresponding second accuracy;

[0101] The target remote sensing data of all sub-areas are fused to obtain fused remote sensing data.

[0102] The shooting area can be divided into multiple sub-areas using Geographic Information System (GIS) software or remote sensing image processing software. By dividing a large shooting area into multiple small areas, it is easier to identify and process details and changes in the data. The shooting area can be divided into multiple sub-areas based on grids, based on terrain features, or based on administrative boundaries.

[0103] The first accuracy refers to the accuracy of the corrected first remote sensing data. The first accuracy may include spatial resolution, spectral resolution, and temporal resolution.

[0104] The second accuracy refers to the accuracy of the second remote sensing data with color information. The second accuracy may include spatial resolution, spectral resolution, etc.

[0105] According to the accuracy information (first accuracy and second accuracy) of each sub-region, determine which data should be given priority in the fusion process. Finally, when there is no obvious overlap or difference between sub-regions, the target remote sensing data of each sub-region can be directly spliced ​​together to form a complete fused remote sensing data. When there is overlap or difference between sub-regions, the target remote sensing data of each sub-region can be fused using linear interpolation, bilinear interpolation or higher-order interpolation algorithms to smoothly transition and fuse the data.

[0106] After obtaining the fused remote sensing data, the fused remote sensing data can be classified and identified to extract useful information. GIS software or visualization tools are also used to display the fused remote sensing data in the form of graphics or charts. A fusion strategy based on sub-region accuracy assessment is used to divide the shooting area into multiple sub-regions and obtain the accuracy information of each sub-region to determine the target remote sensing data of each sub-region. Then, a suitable fusion method is used to fuse the target remote sensing data of all sub-regions into a complete fused remote sensing data.

[0107] Since different areas may be affected by different environmental factors, observation conditions or data source characteristics, resulting in differences in data quality, the above optional implementation method divides the entire shooting area into multiple sub-areas, which can process remote sensing data more finely. For each sub-area, the first accuracy of the corrected first remote sensing data and the second accuracy of the second remote sensing data with color information are obtained respectively to quantify the accuracy or reliability of different data sources in each sub-area. Based on the comparison results of the first accuracy and the second accuracy, the target remote sensing data of the sub-area is determined. Finally, the optimal data sources of different sub-areas are integrated together to form a complete, accurate and information-rich remote sensing data set. The sub-area-based refined processing strategy helps to generate remote sensing data that better meets actual application needs and improves the overall data quality.

[0108] In an optional implementation manner, determining the target remote sensing data of the sub-area according to the first accuracy and the corresponding second accuracy includes:

[0109] comparing the first precision with the corresponding second precision;

[0110] When the first precision is higher than the second precision, using the second remote sensing data with color information as the target remote sensing data of the sub-region;

[0111] When the first accuracy is lower than the second accuracy, the corrected first remote sensing data is used as the target remote sensing data of the sub-area.

[0112] By comparing the first accuracy (the accuracy of the corrected first remote sensing data) and the second accuracy (the accuracy of the second remote sensing data with color information), the target remote sensing data of each sub-area is determined.

[0113] If the accuracy of the corrected first remote sensing data in a specific sub-region is higher than that of the second remote sensing data with color information, it is considered that the first remote sensing data provides more accurate and reliable information in the sub-region. Selecting the corrected first remote sensing data as the target remote sensing data of the sub-region can ensure that the fused remote sensing data is optimized in accuracy, thereby improving the quality of the overall data.

[0114] If the accuracy of the second remote sensing data with color information in a specific sub-region is higher than that of the corrected first remote sensing data, it is considered that the second remote sensing data provides more accurate and richer information in the sub-region. Selecting the second remote sensing data with color information as the target remote sensing data of the sub-region can ensure that the fused remote sensing data has a higher accuracy while maintaining the color information.

[0115] The above optional implementation method can ensure that the remote sensing data with the highest accuracy is selected as the target remote sensing data in each sub-region through accuracy comparison. Selecting a high-precision data source as the target remote sensing data increases the credibility of the fused remote sensing data. Fusion based on the most accurate data source in each sub-region helps to improve the overall quality of the fused remote sensing data, and the fusion results can better reflect the actual conditions of different regions.

[0116] In an optional embodiment, the method further comprises:

[0117] Performing cloud recognition on the fused remote sensing data to obtain a cloud detection result;

[0118] According to the cloud detection result, the fused remote sensing data is repaired to obtain target fused remote sensing data.

[0119] Since cloud cover can lead to the loss of key information in remote sensing data, thus affecting the integrity and accuracy of the data, after fusing remote sensing data, cloud recognition and repair of cloud-covered areas can ensure the quality of fused remote sensing data.

[0120] Cloud recognition technology can be used to identify clouds in fused remote sensing data to obtain cloud detection results. Cloud recognition technology distinguishes clouds from other surface covers based on the spectral characteristics and texture characteristics in remote sensing images. Clouds usually appear as bright areas in remote sensing images, and their spectral characteristics are significantly different from those of the surrounding surface covers. By extracting and analyzing these features, accurate identification of clouds can be achieved. Cloud recognition methods can include: threshold segmentation method, using machine learning algorithms such as support vector machine (SVM) and random forest (RF), and using deep learning models such as convolutional neural network (CNN).

[0121] Analyze the cloud detection results, determine the area blocked by clouds and its size, and perform repair processing on the fused remote sensing data based on the area blocked by clouds and its size. The purpose of the repair processing is to fill the area blocked by clouds to restore the integrity and accuracy of the data. The repair processing of fused remote sensing data can be achieved based on technologies such as image interpolation, image repair algorithm or time series analysis.

[0122] The above optional implementation manner, through cloud identification and repair processing, can reduce data errors caused by cloud occlusion, fill in data missing caused by cloud occlusion, and thus improve the overall quality of remote sensing data.

[0123] Figure 2 It is a functional module diagram of the multi-source remote sensing data processing device provided in an embodiment of the present application.

[0124] In some embodiments, the multi-source remote sensing data processing device 20 may include a plurality of functional modules composed of program code segments. The program code of each program segment in the multi-source remote sensing data processing device 20 may be stored in a memory of a computer device and executed by at least one processor to perform (see Figure 1 Description) Functions for multi-source remote sensing data processing.

[0125] In this embodiment, the multi-source remote sensing data processing device 20 can be divided into multiple functional modules according to the functions it performs. The functional modules may include: a correction module 201, a registration module 202, a mapping module 203, a fusion module 204, a recognition module 205 and a repair module 206. The module referred to in this application refers to a series of computer-readable instruction segments that can be executed by at least one processor and can complete a fixed function, which is stored in a memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments.

[0126] The correction module 201 is used to perform correction processing on the first remote sensing data;

[0127] The registration module 202 is used to register the second remote sensing data based on the corrected first remote sensing data;

[0128] The mapping module 203 is used to map the color information of the corrected first remote sensing data onto the registered second remote sensing data;

[0129] The fusion module 204 is used to fuse the second remote sensing data with color information with the corrected first remote sensing data to obtain fused remote sensing data;

[0130] The identification module 205 is used to perform cloud identification on the fused remote sensing data to obtain a cloud detection result;

[0131] The repair module 206 is used to repair the fused remote sensing data according to the cloud detection result to obtain target fused remote sensing data.

[0132] It should be understood that the various variations and specific embodiments of the multi-source remote sensing data processing method provided in the above-mentioned embodiment are also applicable to the multi-source remote sensing data processing device in the present embodiment. Through the detailed description of the aforementioned multi-source remote sensing data processing method, those skilled in the art can clearly understand the implementation process of the multi-source remote sensing data processing device in the present embodiment. For the sake of brevity of the specification, it will not be described in detail here.

[0133] An embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, all or part of the steps of the multi-source remote sensing data processing method are implemented.

[0134] See also Figure 3 FIG. 2 is a schematic diagram of the structure of a computer device provided in an embodiment of the present application. In a preferred embodiment of the present application, the computer device 3 includes a memory 301 , at least one processor 302 , and at least one communication bus 303 .

[0135] Those skilled in the art should understand that Figure 3 The structure of the computer device shown does not constitute a limitation of the embodiments of the present application. The computer device 3 may also include more or less other hardware or software than shown in the figure, or a different arrangement of components.

[0136] In some embodiments, the computer device 3 is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application-specific integrated circuits, programmable gate arrays, digital processors, and embedded devices. The computer device 3 may also include client devices, which include but are not limited to any electronic product that can interact with the client through a keyboard, mouse, remote control, touchpad, or voice control device, such as a personal computer, tablet computer, smart phone, digital camera, etc.

[0137] It should be noted that the computer device 3 is only an example, and other existing or future electronic products that are suitable for the present application should also be included in the protection scope of the present application and included here by reference.

[0138] In some embodiments, the memory 301 stores a computer program, and when the computer program is executed by the at least one processor 302, all or part of the steps in the multi-source remote sensing data processing method as described above are implemented. The memory 301 includes a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data. Further, the computer-readable storage medium may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function, and the like.

[0139] In some embodiments, the at least one processor 302 is the control core (CrolUnit) of the computer device 3, and uses various interfaces and lines to connect the various components of the entire computer device 3, and executes various functions and processes data of the computer device 3 by running or executing the program or module stored in the memory 301, and calling the data stored in the memory 301. For example, when the at least one processor 302 executes the computer program stored in the memory, it implements all or part of the steps of the multi-source remote sensing data processing method described in the embodiment of the present application; or implements all or part of the functions of the multi-source remote sensing data processing device. The at least one processor 302 can be composed of an integrated circuit, for example, it can be composed of a single packaged integrated circuit, or it can be composed of multiple integrated circuits with the same function or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips.

[0140] In some embodiments, the at least one communication bus 303 is configured to realize connection and communication between the memory 301 and the at least one processor 302, etc. Although not shown, the computer device 3 may also include a power supply (such as a battery) for powering each component. Preferably, the power supply may be logically connected to the at least one processor 302 through a power management device, so as to realize functions such as management of charging, discharging, and power consumption management through the power management device. The power supply may also include any components such as one or more DC or AC power supplies, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, etc. The computer device 3 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0141] The above-mentioned integrated unit implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a computer device, or a network device, etc.) or a processor to execute part of the method described in each embodiment of the present application.

[0142] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0143] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

Claims

1. A multi-source remote sensing data processing method, characterized in that: The method comprises: performing correction processing on the first remote sensing data; Based on the corrected first remote sensing data, registering the second remote sensing data; Mapping the color information of the corrected first remote sensing data onto the registered second remote sensing data; The second remote sensing data with color information is fused with the corrected first remote sensing data to obtain fused remote sensing data.

2. The multi-source remote sensing data processing method according to claim 1, characterized in that: The correction processing of the first remote sensing data comprises: Acquiring image characteristics of the first remote sensing data; Obtain application requirements; Selecting a target correction processing model from a plurality of preset correction processing models according to the image characteristics and the application requirements; The first remote sensing data is corrected using the target correction processing model.

3. The multi-source remote sensing data processing method according to claim 1, characterized in that: Mapping the color information of the corrected first remote sensing data onto the registered second remote sensing data comprises: Acquiring lighting information when the first remote sensing data is captured; Performing illumination compensation on the corrected first remote sensing data according to the illumination information; According to the pre-established mapping relationship between the first remote sensing data and the second remote sensing data, the color information of the first remote sensing data after illumination compensation is mapped to the second remote sensing data after registration.

4. The multi-source remote sensing data processing method according to claim 3, characterized in that: The performing illumination compensation on the corrected first remote sensing data according to the illumination information comprises: Determining the degree of influence of the illumination information on the color information of the first remote sensing data; Determining a light compensation parameter according to the degree of influence; Perform illumination compensation on the corrected first remote sensing data according to the illumination compensation parameter.

5. The multi-source remote sensing data processing method according to any one of claims 1 to 4, characterized in that: The fusing the second remote sensing data with the color information with the corrected first remote sensing data to obtain the fused remote sensing data comprises: Divide the shooting area into multiple sub-areas; Acquire a first precision of the corrected first remote sensing data of each sub-region; Acquire the second precision of the second remote sensing data with color information for each sub-region; For each sub-region, determining target remote sensing data of the sub-region according to the first accuracy and the corresponding second accuracy; The target remote sensing data of all sub-areas are fused to obtain fused remote sensing data.

6. The multi-source remote sensing data processing method according to claim 5, characterized in that: The determining the target remote sensing data of the sub-area according to the first accuracy and the corresponding second accuracy includes: comparing the first precision with the corresponding second precision; When the first precision is higher than the second precision, using the second remote sensing data with color information as the target remote sensing data of the sub-region; When the first accuracy is lower than the second accuracy, the corrected first remote sensing data is used as the target remote sensing data of the sub-area.

7. The multi-source remote sensing data processing method according to claim 1, characterized in that: The method further comprises: Performing cloud recognition on the fused remote sensing data to obtain a cloud detection result; According to the cloud detection result, the fused remote sensing data is repaired to obtain target fused remote sensing data.

8. A multi-source remote sensing data processing device, characterized in that: The device comprises: A correction module, used for performing correction processing on the first remote sensing data; A registration module, used for registering the second remote sensing data based on the corrected first remote sensing data; A mapping module, used for mapping the color information of the corrected first remote sensing data onto the registered second remote sensing data; The fusion module is used to fuse the second remote sensing data with the color information with the corrected first remote sensing data to obtain fused remote sensing data.

9. A computer device, characterized in that: The computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the multi-source remote sensing data processing method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the multi-source remote sensing data processing method as claimed in any one of claims 1 to 7 are implemented.

Images