Construction method and device of remote sensing image block adjustment result precision lookup table

Abstract

The embodiment of the invention provides a method and device for constructing a remote sensing image block adjustment result precision lookup table, and is applied to the technical field of remote sensing application. The method comprises the following steps: respectively calculating the area and proportion of each land surface coverage type and each terrain type in a block adjustment network, and collecting sufficient and uniformly distributed detection points required for calculating the accuracy of a remote sensing image block adjustment result in a measurement area range; designing a sequence of the number and the position of sample detection points corresponding to each terrain coverage type on each terrain type, calculating a median error sequence corresponding to each number of sample detection points, and counting the relationship between the adjustment result precision and the area and the proportion of the terrain and the terrain type, and the number and the distribution of the detection points; and obtaining the minimum number of check points required by block adjustment result precision check through a marginal effect, and constructing a remote sensing image block adjustment result precision lookup table. In conclusion, the uncertainty of block adjustment result detection caused by point selection number difference and non-uniform position distribution can be avoided.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, in particular to the field of remote sensing application technology, and specifically to a method and device for constructing an accuracy lookup table of remote sensing image regional network adjustment results. Background Art

[0002] The quality inspection of surveying and mapping products is an important part of controlling the quality of surveying and mapping products. Among them, the quality inspection of 4D surveying and mapping products such as Digital Orthophoto Map (DOM), Digital Line Graphic (DLG), Digital Elevation Model (DEM) and Digital Raster Graphic (DRG) has corresponding national standards or industry standards to follow, and the quality inspection of non-4D products such as single-view orthorectified image products can refer to 4D products.

[0003] However, there are currently no technical regulations or standards that can be used as a basis or reference for the remote sensing image results of regional network adjustment, which leads to uncertainty in the quality inspection results of regional network adjustment results. At the same time, in the scenario of large-scale mapping abroad, there is a lack of a complete and reliable source of geometric feature reference point data. This has brought great challenges to mapping work and verification of mapping results.

[0004] Due to the diversity of open source data, there are large differences in accuracy, timeliness and resolution, so it is difficult to mine such data information. Currently, there is no complete set of information mining methods. It is an urgent problem to collect and organize existing open source data and prepare a set of reliable reference information sources.

[0005] In summary, there are two main problems with the existing technology for quality inspection of the accuracy of remote sensing image block adjustment results: first, it is impossible to determine the typicality and representativeness of the selected point locations; second, it is impossible to determine whether the number of detection points can meet the requirements of block adjustment accuracy inspection. Summary of the invention

[0006] The present invention provides a method and device for constructing a remote sensing image regional network adjustment result accuracy lookup table.

[0007] According to a first aspect of the present disclosure, a method for constructing a remote sensing image block adjustment result accuracy lookup table is provided. The method comprises: Obtain the land cover type data and terrain elevation data within the survey area of ​​the remote sensing image regional network adjustment; According to the surface cover type data and the terrain elevation data, the area and proportion of each surface cover type on each terrain type in the survey area of ​​the regional network adjustment are calculated respectively; According to the land cover type data and terrain elevation data, collect enough and evenly distributed test points within the survey area to calculate the accuracy of the sample test points required for the regional network adjustment results of remote sensing images; Design the sequence of the number and location of sample detection points corresponding to each surface coverage type on each terrain type, and calculate the mean error sequence corresponding to each number of sample detection points; Based on the error sequence of sample detection points corresponding to each surface coverage type on each terrain type, the relationship between the accuracy of adjustment results and the area and proportion of terrain and land types, as well as the number and distribution of detection points is statistically analyzed. The minimum number of checkpoints required for accuracy inspection of regional network adjustment results is obtained through marginal effect, and an accuracy lookup table for remote sensing image regional network adjustment results is constructed.

[0008] According to the above aspects and any possible implementation, an implementation is further provided, wherein the designing of a sequence of the number and position of sample detection points corresponding to each surface coverage type on each terrain type, and calculating a mean error sequence corresponding to each number of sample detection points comprises: Based on a preset detection point distribution algorithm, the number and location of sample detection points on each surface coverage type on each terrain type are determined according to the area and proportion within the survey area of ​​the regional network adjustment of each surface coverage type on each terrain type, as well as the number and distribution of the detection points; According to the number and position of sample detection points on each surface coverage type on each terrain type, the mean error sequence of the sample detection points corresponding to each surface coverage type on each terrain type is calculated. The mean error sequence of the sample detection points corresponding to each surface coverage type on each terrain type records the mean error information calculated under different strategies in the form of a list.

[0009] According to the above aspects and any possible implementation, an implementation is further provided, wherein the error sequence in the sample detection points corresponding to each surface coverage type on each terrain type is based on the relationship between the accuracy of the adjustment result and the area and proportion of the terrain and land type, as well as the number and distribution of the detection points, and the minimum number of checkpoints required for the accuracy check of the regional network adjustment result is obtained through the marginal effect, and the remote sensing image regional network adjustment result accuracy lookup table is constructed, which includes: By using the marginal effect of the mean error of the detection point, a linear fitting is performed on the mean error sequence of the sample detection points corresponding to each surface coverage type on each terrain type, with the number of sample detection points as the horizontal axis and the mean error as the vertical axis, and the stationary point is calculated; wherein the mean error sequence of the sample detection points corresponding to each surface coverage type on each terrain type includes a mean error sequence of a single surface coverage type corresponding to a single terrain type or a mean error sequence of a single terrain type corresponding to a single surface coverage type; According to the station points corresponding to each surface coverage type on each terrain type, the number of sample detection points corresponding to each station point is calculated to obtain the minimum number of checkpoints; The influence weights of terrain type and land cover type are determined according to the number of sample detection points corresponding to each station; According to the influence weight, the area and proportion of the survey area of ​​the remote sensing image regional network adjustment of each surface coverage type on each terrain type, and the number and distribution of the detection points, the corresponding minimum number of detection points is obtained, and the accuracy lookup table of the remote sensing image regional network adjustment results is constructed.

[0010] According to the above aspects and any possible implementation, an implementation is further provided, wherein obtaining the surface coverage type data and terrain elevation data in the survey area of ​​the remote sensing image regional network adjustment comprises: According to the resolution and accuracy of the adjustment results of the remote sensing image regional network adjustment in the survey area, the initial data of the surface coverage type and the initial data of the terrain elevation in the survey area are obtained; According to the type, resolution and accuracy of the acquired data, the initial data of land cover type and initial data of terrain elevation are sorted in different scales; Rename the sorted initial data of land cover types and initial data of terrain elevation according to preset rules, and store them in the database according to pixel locations to complete the construction of the background library of geographic conditions for regional block adjustment; The surface coverage type data and terrain elevation data within the survey area of ​​the remote sensing image block adjustment are obtained from the block adjustment geographic condition background library.

[0011] According to the above aspects and any possible implementation, an implementation is further provided, wherein the calculating, based on the surface cover type data and the terrain elevation data, the area and proportion of each surface cover type in each terrain type within the survey area of ​​the regional network adjustment comprises: According to a preset resolution, the surface cover type data and the terrain elevation data are normalized, wherein the normalization is to construct a complete resolution and precision multi-level continuous regional network adjustment geographic condition background library pyramid data body; According to the normalized surface cover type data and terrain elevation data, the area and proportion of each surface cover type in the survey area of ​​regional network adjustment are calculated respectively.

[0012] According to the above aspects and any possible implementation, an implementation is further provided, wherein the detection points for collecting a sufficient number of uniformly distributed sample detection points required for calculating the accuracy of the remote sensing image regional network adjustment results within the survey area based on the surface cover type data and the terrain elevation data include: Based on the preset detection point extraction model, the number and distribution of sample detection points required for the accuracy of the remote sensing image regional network adjustment results are collected and determined; the sample detection points are reliable and sufficient in number.

[0013] According to the aspects described above and any possible implementation methods, an implementation method is further provided, wherein the surface cover type data includes cultivated land, forest land, grassland, shrubland, wetland, water body, tundra, artificial surface, bare land, glacier and permanent snow; the terrain elevation data includes terrain categories, and the terrain categories include alpine land, mountainous land, hills and plains.

[0014] According to a second aspect of the present disclosure, a device for constructing a remote sensing image block adjustment result accuracy lookup table is provided. The device comprises: The acquisition module is used to obtain the surface coverage type data and terrain elevation data in the survey area of ​​the remote sensing image regional network adjustment; A processing module, for calculating the area and proportion of each surface cover type on each terrain type in the survey area of ​​the regional network adjustment according to the surface cover type data and the terrain elevation data; The processing module is also used to collect a sufficient number of uniformly distributed detection points within the survey area for calculating the accuracy of the sample detection points required for the remote sensing image regional network adjustment results according to the surface cover type data and the terrain elevation data; The processing module is also used to design a sequence of the number and position of sample detection points corresponding to each surface coverage type on each terrain type, and calculate the mean error sequence corresponding to each number of sample detection points; The generation module is used to calculate the relationship between the accuracy of the adjustment results and the area and proportion of terrain and land types, as well as the number and distribution of the detection points based on the error sequence of the sample detection points corresponding to each surface coverage type on each terrain type. The minimum number of checkpoints required for the accuracy check of the regional network adjustment results is obtained through the marginal effect, and the accuracy lookup table of the remote sensing image regional network adjustment results is constructed.

[0015] According to a third aspect of the present disclosure, an electronic device is provided, which includes a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the program, the method described above is implemented.

[0016] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method described above is implemented.

[0017] The embodiment of the present application provides a method and device for constructing a lookup table for the accuracy of a remote sensing image regional network adjustment result. The method and device can obtain the surface coverage type data and terrain elevation data in the survey area of ​​the remote sensing image regional network adjustment; then, based on the surface coverage type data and the terrain elevation data, respectively calculate the area and proportion of each surface coverage type in the survey area of ​​the regional network adjustment on each terrain type; then, based on the surface coverage type data and the terrain elevation data, collect a sufficient number of uniformly distributed detection points within the survey area to calculate the sample detection points required for the accuracy of the remote sensing image regional network adjustment result; then design a sequence of the number and position of sample detection points corresponding to each surface coverage type on each terrain type, and calculate each The mean error sequence corresponding to the number of sample detection points is obtained; based on the mean error sequence of sample detection points corresponding to each surface coverage type on each terrain type, the relationship between the accuracy of the adjustment results and the area and proportion of terrain and land types, as well as the number and distribution of detection points are statistically analyzed, and the minimum number of checkpoints required for the accuracy check of the regional block adjustment results is obtained through the marginal effect, and the accuracy lookup table of the remote sensing image regional block adjustment results is constructed; based on this, the method of constructing the accuracy lookup table of the remote sensing image regional block adjustment results can be used to establish the relationship between the accuracy of the regional block adjustment results and the point location, surface coverage and terrain conditions and the number of points, so as to avoid the uncertainty of the regional block adjustment result detection caused by the difference in the number of selected points and the uneven distribution of positions.

[0018] It should be understood that the contents described in the summary of the invention are not intended to limit the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, among which: Figure 1 A flowchart of a method for constructing a remote sensing image block adjustment result accuracy lookup table according to an embodiment of the present disclosure is shown; Figure 2 A block diagram of a device for constructing a remote sensing image block adjustment result accuracy lookup table according to an embodiment of the present disclosure is shown; Figure 3 A block diagram of an exemplary electronic device capable of implementing embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0021] In addition, the term "and / or" in this article is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0022] In the present disclosure, a method of constructing a remote sensing image regional block adjustment result accuracy lookup table can be used to establish the relationship between the accuracy of the regional block adjustment result and the point location, surface coverage and terrain conditions, and the number of points, thereby avoiding the uncertainty of regional block adjustment result detection caused by differences in the number of selected points and uneven location distribution.

[0023] Figure 1 A flowchart of a method 100 for constructing a remote sensing image block adjustment result accuracy lookup table according to an embodiment of the present disclosure is shown.

[0024] In block 110 , the land cover type data and terrain elevation data within the survey area of ​​the remote sensing image block adjustment are obtained.

[0025] In block 120, the area and proportion of each land cover type in the survey area of ​​the regional block adjustment are calculated based on the land cover type data and the terrain elevation data.

[0026] In block 130, based on the land cover type data and the terrain elevation data, a sufficient number of evenly distributed test points are collected within the survey area to calculate the sample test points required for the accuracy of the remote sensing image regional network adjustment results.

[0027] In block 140 , a sequence of the number and position of sample detection points corresponding to each surface coverage type on each terrain type is designed, and a mean error sequence corresponding to each number of sample detection points is calculated.

[0028] In box 150, based on the error sequence in the sample detection points corresponding to each surface coverage type on each terrain type, the relationship between the accuracy of the adjustment results and the area and proportion of the terrain and land types, as well as the number and distribution of the detection points is statistically analyzed, and the minimum number of checkpoints required for the accuracy check of the regional network adjustment results is obtained through the marginal effect, and a remote sensing image regional network adjustment result accuracy lookup table is constructed.

[0029] In block 110, a block adjustment geographic condition background library may be established, and surface coverage type data and terrain elevation data within a survey area of ​​remote sensing image block adjustment may be obtained from the block adjustment geographic condition background library.

[0030] In some embodiments, various types of geographic condition data, such as various types of surface cover type data and terrain elevation data, are collected within the survey area according to the regional scope of the remote sensing image regional block adjustment. A regional block adjustment geographic condition background database is established through a comprehensive analysis of multi-resolution and multi-type data combined with the resolution and accuracy of the regional block adjustment data. In the regional block adjustment geographic condition background database, the surface cover type data and terrain elevation data can be stored according to the pixel position.

[0031] In some embodiments, the above-mentioned acquisition of land cover type data and terrain elevation data in the survey area for remote sensing image block adjustment includes: According to the resolution and accuracy of the adjustment results of the remote sensing image regional network adjustment in the survey area, the initial data of the surface coverage type and the initial data of the terrain elevation in the survey area are obtained; According to the type, resolution and accuracy of the acquired data, the initial data of land cover type and terrain elevation are sorted in different scales; Rename the sorted initial data of land cover types and initial data of terrain elevation according to preset rules, and store them in the database according to pixel locations to complete the construction of the background library of geographic conditions for regional block adjustment; The surface coverage type data and terrain elevation data within the survey area of ​​the remote sensing image block adjustment are obtained from the block adjustment geographic condition background library.

[0032] In some embodiments, based on the basic conditions of the survey area such as the scope of the regional network adjustment area, the resolution and accuracy of the adjustment data, the geographical condition data such as the surface cover type data and the terrain elevation data within the survey area that need to be quality inspected can be collected. During the collection process, data with better resolution and accuracy should be collected as a reference, that is, the initial data of the surface cover type and the initial data of the terrain elevation within the survey area.

[0033] In some embodiments, initial data of land cover types with different resolutions can be selected according to actual needs. For example, the IGBP (International Geosphere Biosphere Programme) land cover classification scheme provided by the MODIS (Moderate Resolution Imaging Spectroradiometer) land cover type product is selected, with a resolution of 500 meters and 17 types of land types, which is suitable for the needs of imprecise land types; the GlobeLand30 remote sensing mapping dataset is selected, with a resolution of 30 meters and 10 types of land types, which is suitable for the needs of more precise land types.

[0034] In some embodiments, the initial terrain elevation data can use an open source dataset. The global SRTM (Shuttle Radar Topography Mission) data includes datasets with different resolutions of 30 meters and 90 meters, covering a range between 56 degrees south latitude and 61 degrees north latitude. The high-latitude terrain elevation initial data can select other types of datasets, such as ASTER GDEM (Advanced Spaceborne Theemal Emission and Reflection RadiometerGlobal Digital Elevation Model), and the latitude coverage range can be between 83 degrees north latitude.

[0035] In some embodiments, the acquired data may be sorted and analyzed to facilitate subsequent operations. Specifically, the acquired geographical condition data may be arranged in ascending order of different scales according to different data types, resolutions and accuracies, the initial data of land cover types and initial data of terrain elevation may be accurately matched, and the multi-source data may be comprehensively analyzed. If necessary, the resolution may be normalized to the same scale by constructing a pyramid to achieve the correspondence between multi-source data at the same scale.

[0036] In some embodiments, the multi-source geographic condition data that is collated and analyzed can be renamed according to preset rules and stored in a database for subsequent use. The corresponding relationship between multi-source data at different scales can be effectively distinguished through naming, laying a foundation for subsequent applications. Among them, the preset rules can be set according to the actual needs of the user.

[0037] For example, the naming method can be selected as "Dataset Category Data Source Name Resolution Data Accuracy", and the accuracy can be omitted. For example, the land cover type data can be named "LAND USE CLASSIFICATION_GlobeLand30_30m", which represents the GlobeLand30 land cover type product with a spatial resolution of 30 meters; the terrain elevation data can be named "DEM_SRTM_30m_10m", which represents the SRTM (Shuttle Radar Topography Mission) terrain elevation data with a spatial resolution of 30 meters and an accuracy of 10 meters.

[0038] In block 120, the area and proportion of each surface cover type in the block adjustment survey area can be calculated based on the surface cover type data and terrain elevation data by analyzing the background database of regional geographical conditions in the block adjustment area.

[0039] Specifically, the required scale resolution can be determined according to the quality inspection requirements of the regional network adjustment data, the surface cover type data and the terrain elevation data can be spatially normalized for consistency, and then the normalized surface cover type data and terrain elevation data can be used to calculate the area and proportion of each surface cover type and each terrain type in the survey area.

[0040] In some embodiments, the above-mentioned calculation of the area and proportion of each surface cover type in the survey area of ​​the regional block adjustment on each terrain type according to the surface cover type data and the terrain elevation data includes: According to the preset resolution, the surface cover type data and terrain elevation data are normalized. The normalization process is to build a complete resolution and precision multi-level continuous regional network adjustment geographic condition background library pyramid data body; According to the normalized surface cover type data and terrain elevation data, the area and proportion of each surface cover type in the survey area of ​​regional network adjustment are calculated respectively.

[0041] In some embodiments, after the data is collected and organized into the regional network adjustment geographic condition background library, the existing results can be analyzed for multi-scale data sources. If the data to be inspected, that is, the surface cover type data and the terrain elevation data, have clear scale requirements, such as precision quality inspection, high-precision quality inspection, etc., the scale that best meets the requirements will be extracted, and further analysis will be performed on whether there are differences in resolution and accuracy of the multi-source data of geographic conditions at this scale. If there are differences, further normalization processing is required to unify the indicators of the multi-source data of geographic conditions at this scale; if there is no clear scale requirement, all multi-source data of geographic conditions will be analyzed at multiple scales.

[0042] For example, if the scale requirement of the data to be inspected is a quality inspection with the same accuracy at a spatial resolution of 30 meters, then the GlobeLand30 land cover type product with a spatial resolution of 30 meters, the SRTM terrain elevation data with a spatial resolution of 30 meters and an accuracy of 10 meters, and the ASTER GDEM terrain elevation data with a spatial resolution of 30 meters and an accuracy of 7-14 meters can be used directly, while the MODIS land cover type product with a spatial resolution of 500 meters needs to be resampled to a scale of 30 meters to achieve consistency in spatial scale, that is, normalization. If the scale requirement of the data to be inspected is a high-precision quality inspection with a spatial resolution of 30 meters, it is necessary to collect data with a higher spatial resolution to achieve high-precision quality inspection, such as collecting land cover type data and terrain elevation data products with a spatial resolution of 10 meters.

[0043] In some embodiments, multi-source data of geographical conditions at a selected scale, i.e., normalized surface cover type data and terrain elevation data, are subjected to multi-dimensional extraction, such as area and proportion. The terrain elevation data and surface cover type data contained in the regional network adjustment geographical condition background library can be distinguished at the same scale according to the terrain categories of high mountains, mountains, hills and plains of the terrain elevation data, and area and proportion statistics are performed. Among them, the terrain category can be classified by slope according to the terrain elevation data, or the existing terrain classification vector data can be collected and used directly. Then, according to the GlobeLand30 surface cover type data, cultivated land, forest land, grassland, shrub land, wetland, water body, tundra, artificial surface, bare land, glacier and permanent snow, etc., the area and proportion statistics are performed. The area and proportion of each surface cover type in each terrain type in the survey area of ​​the regional network adjustment are shown in Table 1.

[0044] Table 1: Area and proportion of each surface coverage type in the survey area of ​​regional block adjustment for each terrain type In box 130, a scheme for selecting the number and distribution of position accuracy detection points under composite multi-scenario conditions of various terrain types and surface cover types can be designed. According to the designed scheme, the detection points are first selected automatically by computer, and then manually verified after the automatic point selection to eliminate the automatically selected pseudo detection points, that is, the points with large errors, and supplement the detection points that do not meet the design requirements. Finally, a sufficient number of reliable detection points are obtained to complete the acquisition of the detection points of the sample detection points required for calculating the accuracy of the remote sensing image regional network adjustment results.

[0045] It should be noted that in the process of constructing the accuracy lookup table of the remote sensing image regional block adjustment results, the surface coverage and terrain data can also be directly obtained to select sample detection points. The establishment and analysis of the regional block adjustment geographical condition background library belongs to data preprocessing, so as to further refine the relationship between the accuracy of the regional block adjustment results and the point location, surface coverage and terrain conditions and the number of points, so as to further avoid the uncertainty of the regional block adjustment result detection caused by differences in the number of selected points and uneven location distribution.

[0046] In some embodiments, based on the land cover type data and terrain elevation data, the detection points of the sample detection points required for calculating the accuracy of the remote sensing image regional network adjustment results, which are collected in a sufficient number and evenly distributed within the measurement area, include: Based on the preset detection point extraction model, the detection points of the sample detection points required for the accuracy of the remote sensing image regional network adjustment results are collected and determined. The detection points are reliable and sufficient in number.

[0047] In some embodiments, based on the analysis of various terrain types and surface coverage composite multi-scenario conditions within the survey area, implementation plans are selected for various combinations of design data volume and reasonably distributed position accuracy detection points. The design of the plan needs to comprehensively consider the various surface coverage conditions in each terrain type, design the relationship between terrain types and surface coverage according to actual needs, and appropriately choose unnecessary combinations.

[0048] In some embodiments, non-existent terrain categories and surface cover types are deleted according to the actual situation within the survey area; when there are many surface cover types, they can also be merged according to actual needs, such as merging woodlands, grasslands, shrublands, and wetlands into vegetation.

[0049] In some embodiments, by using suitable software to automatically select checkpoints according to the designed point selection plan, and using the automatically selected checkpoints as alternative data sources, the computer can greatly save time costs and facilitate the rapid completion of work tasks.

[0050] It should be noted that the software for automatically extracting checkpoints can be selected according to actual conditions. At the same time, the number of checkpoints should be more than the design plan as much as possible to prepare for the subsequent elimination of erroneous points.

[0051] In some embodiments, existing mature commercial software such as ENVI, ARCGIS, GXL and the like may be used for checkpoint extraction, or the required algorithms may be called through various programming tools to achieve the acquisition of checkpoints.

[0052] In some embodiments, the accuracy of the checkpoints automatically selected by the computer can be manually verified to eliminate the checkpoints that do not meet the requirements, and on this basis, the checkpoints that deviate from the design plan can be supplemented to ensure that the number of checkpoints is sufficient.

[0053] In some embodiments, the manual verification stage can use a variety of strategies to confirm the accuracy of the checkpoints, such as arranging the checkpoint errors in ascending and descending order, and giving priority to verifying the points with larger errors; randomly selecting a certain proportion of checkpoints to calculate the mean error, comparing the differences between multiple mean errors, and judging the reliability of the checkpoints, etc. Through this step, sufficient number of plane position checkpoints with reasonable distribution and reliable accuracy can be collected.

[0054] In some embodiments, the mean error calculation formula is as follows: Where S represents the mean error, N represents the number of checkpoints, x and y represent the plane position coordinates of the data to be checked, and X and Y are the position coordinates of the checkpoints with the same name corresponding to the reference image and the data to be checked.

[0055] In block 140, the number of sample detection points can be statistically correlated with the terrain type and the background information of the surface coverage, a stratification scheme of the sample detection points can be designed, and the detection points can be stratified according to the stratification scheme using a random algorithm. The stratification scheme should take into account the number of sample detection points and the distribution of different terrain types and surface coverage in the survey area, and the sample detection points after stratification can be calculated using the mean error formula, and the error results can be statistically correlated with the terrain type and the surface coverage.

[0056] In some embodiments, the above-mentioned designing the sequence of the number and position of sample detection points corresponding to each surface coverage type on each terrain type, and calculating the mean error sequence corresponding to each number of sample detection points includes: Based on the preset detection point distribution algorithm, the number and location of sample detection points on each surface coverage type on each terrain type are determined according to the area and proportion within the survey area of ​​the regional network adjustment of each surface coverage type on each terrain type, as well as the number and distribution of detection points; According to the number and location of sample detection points on each surface coverage type on each terrain type, the mean error sequence of sample detection points corresponding to each surface coverage type on each terrain type is calculated. The mean error sequence of sample detection points corresponding to each surface coverage type on each terrain type records the mean error information calculated under different strategies in the form of a list.

[0057] In some embodiments, in the process of designing a sample checkpoint stratification scheme, a random algorithm, that is, a preset checkpoint distribution algorithm, can be used to stratify the sample checkpoints according to the stratification scheme. The stratification scheme should take into account the number of sample checkpoints and the distribution of the sample checkpoints in different terrain categories and surface coverage in the survey area to ensure that each terrain category and surface coverage type required for quality inspection has a sufficient number of points in the sample checkpoint distribution for subsequent analysis.

[0058] For example, in this process, the terrain category can be used as the first level of classification, and the survey area can be divided into four parts: plain, hilly, mountainous and high mountainous areas. The surface cover category is then introduced into each type of terrain classification. On the basis of the four types of terrain categories, different numbers of sample detection points are selected in different surface cover type areas to calculate the mean error.

[0059] In some embodiments, the sample detection points after stratification can be used to calculate the error using the mean error formula, and the plane geometric position accuracy results can be statistically associated with the terrain category and the surface coverage using a stratified scheme.

[0060] For example, under full consideration of the geographical conditions of terrain type and surface coverage, the mean errors calculated from different numbers of sample detection points are statistically analyzed. The number of sample detection points can be selected by designing an arithmetic progression based on actual conditions, such as 5, 10, 15, 20..., and these different numbers of sample detection points are required to be evenly distributed in the survey area, and the mean error information calculated under different strategies is recorded in the form of a list.

[0061] Specifically, the error results are first obtained by introducing the land cover type according to the terrain classification, and can be listed in four tables classified by terrain category. Each table represents a type of terrain category, and the mean error of different numbers of sample detection points under different land cover types is counted. If it is necessary to count the sample inspection points of different numbers of four land cover categories under different terrain conditions, the table shown in Table 2 can be used for statistics, and each type of terrain is listed in a table for independent statistics.

[0062] Table 2: Mean square error for different number of sample checkpoints for four land cover categories under different terrain conditions In box 150, based on the error sequence in the sample detection points corresponding to each surface coverage type on each terrain type, the relationship between the accuracy of the adjustment results and the area and proportion of the terrain and land types, as well as the number and distribution of the detection points is statistically analyzed, and the minimum number of checkpoints required for the accuracy check of the regional network adjustment results is obtained through the marginal effect, and a remote sensing image regional network adjustment result accuracy lookup table is constructed.

[0063] In some embodiments, the above-mentioned error sequence in the sample detection points corresponding to each surface coverage type on each terrain type, the relationship between the accuracy of the statistical adjustment results and the area and proportion, and the number and distribution of the detection points, and the construction of the remote sensing image regional network adjustment result accuracy lookup table includes: By using the marginal effect of the mean error of the detection point, a linear fitting is performed on the mean error sequence of the sample detection points corresponding to each surface cover type on each terrain type, with the number of sample detection points as the horizontal axis and the mean error as the vertical axis, and the stationary point is calculated; wherein, the mean error sequence of the sample detection points corresponding to each surface cover type on each terrain type includes a mean error sequence of a single surface cover type corresponding to a single terrain type or a mean error sequence of a single terrain type corresponding to a single surface cover type; According to the station points corresponding to each surface coverage type on each terrain type, the number of sample detection points corresponding to each station point is calculated to obtain the minimum number of checkpoints; The influence weights of terrain type and land cover type are determined according to the number of sample detection points corresponding to each station; According to the influence weight, the area and proportion of the survey area of ​​the remote sensing image regional network adjustment of each surface coverage type on each terrain type, as well as the number and distribution of detection points, the corresponding minimum number of detection points is obtained, and the accuracy lookup table of the remote sensing image regional network adjustment results is constructed.

[0064] In some embodiments, the mean error calculated from different numbers of sample detection points under multi-source geographical conditions of different terrain categories and surface coverage can be analyzed, that is, the mean error sequence of a single surface coverage corresponding to a single terrain category or the mean error sequence of a single terrain category corresponding to a single surface coverage is linearly fitted with the number of detection points as the horizontal axis and the mean error as the vertical axis, and the stationary point is calculated. The number of detection points corresponding to the mean error at the current position is calculated through the stationary point and recorded, and the stationary point calculation is performed for each type of combination according to different situations, and the number of checkpoints corresponding to the stationary point under each type of combination is counted.

[0065] In some embodiments, linear fitting can be performed using a polynomial fitting method, and the polynomial fitting formula is as follows: Among them, m and n represent the number of points and mean error values ​​corresponding to the horizontal and vertical coordinates, and i is the highest power of the polynomial. The higher the power, the more accurate the curve is, and the greater the amount of calculation is. It is necessary to select a reasonable polynomial and calculate the polynomial coefficients based on the existing data. , thus obtaining the required equation.

[0066] In some embodiments, based on the above calculation results, it can be analyzed whether the influencing factor affecting the final mean error is the terrain category or the surface coverage, and the influence weights of the two geographical condition data on the final result can be obtained, and a plane accuracy detection lookup table can be obtained. The final number of points selected in the survey area must also be combined with the weighting of various classifications of factors with greater influence in the survey area, ultimately ensuring the determination of a reasonable number of checkpoints.

[0067] For example, the number and accuracy of checkpoints are analyzed according to terrain type and surface cover, the impact of the two geographical conditions on the number of checkpoints is compared, and statistical regression analysis is performed to obtain the main influencing factors. The final remote sensing image regional network adjustment result accuracy lookup table is obtained according to the proportion of the survey area obtained by the main influencing factors.

[0068] According to the embodiments of the present disclosure, the following technical effects are achieved: It is possible to obtain the surface coverage type data and terrain elevation data in the survey area of ​​the remote sensing image regional network adjustment; then, based on the surface coverage type data and terrain elevation data, calculate the area and proportion of each surface coverage type in the survey area of ​​the regional network adjustment on each terrain type; then, based on the surface coverage type data and terrain elevation data, collect a sufficient number of uniformly distributed detection points within the survey area to calculate the sample detection points required for the accuracy of the remote sensing image regional network adjustment results; then design a sequence of the number and position of sample detection points corresponding to each surface coverage type on each terrain type, and calculate the mean error sequence corresponding to each number of sample detection points; Based on the error sequence of sample detection points corresponding to each surface coverage type in each terrain type, the relationship between the accuracy of the adjustment results and the area and proportion of terrain and land types, as well as the number and distribution of detection points, is statistically analyzed. The minimum number of checkpoints required for the accuracy check of the regional block adjustment results is obtained through the marginal effect, and a precision lookup table for the regional block adjustment results of remote sensing images is constructed. Based on this, the method of constructing a precision lookup table for the regional block adjustment results of remote sensing images can be used to establish the relationship between the accuracy of the regional block adjustment results and the point location, surface coverage and terrain conditions, and the number of points, so as to avoid the uncertainty of the regional block adjustment result detection caused by differences in the number of selected points and uneven location distribution.

[0069] In some embodiments, the above-mentioned surface cover type data includes cultivated land, forest land, grassland, shrubland, wetland, water body, tundra, artificial surface, bare land, glacier and permanent snow; the above-mentioned terrain elevation data includes terrain categories, and the terrain categories include alpine land, mountainous land, hills and plains.

[0070] It should be noted that land cover types include but are not limited to cultivated land, forest land, grassland, shrub land, wetland, water body, tundra, artificial surface, bare land, glacier and permanent snow, and may also include other land cover types. Terrain types include but are not limited to alpine land, mountainous land, hilly land and plain land, and may also include other terrain types.

[0071] In some embodiments, based on the constructed remote sensing image block adjustment result accuracy lookup table, the user can determine the locations of detection points that are typical and representative and meet the requirements of block adjustment accuracy inspection according to actual needs.

[0072] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present disclosure is not limited by the order of the actions described, because according to the present disclosure, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present disclosure.

[0073] The above is an introduction to the method embodiment. The following is a further explanation of the scheme disclosed in the present invention through an apparatus embodiment.

[0074] Figure 2 FIG. 2 is a block diagram of a device 200 for constructing a remote sensing image block adjustment result accuracy lookup table according to an embodiment of the present disclosure. Figure 2 As shown, the device 200 includes: The acquisition module 210 is used to acquire the land cover type data and terrain elevation data in the survey area of ​​the remote sensing image regional block adjustment; The processing module 220 is used to calculate the area and proportion of each surface cover type in the survey area of ​​the regional network adjustment on each terrain type according to the surface cover type data and the terrain elevation data; The processing module 220 is also used to collect a sufficient number of evenly distributed detection points within the measurement area to calculate the accuracy of the sample detection points required for the remote sensing image regional network adjustment result according to the surface cover type data and the terrain elevation data; The processing module 220 is further used to design a sequence of the number and position of sample detection points corresponding to each surface coverage type on each terrain type, and calculate a mean error sequence corresponding to each number of sample detection points; Generation module 230 is used to calculate the relationship between the accuracy of the adjustment results and the area and proportion of the terrain and land types, as well as the number and distribution of the detection points based on the error sequence in the sample detection points corresponding to each surface coverage type on each terrain type, and to obtain the minimum number of checkpoints required for the accuracy check of the regional network adjustment results through the marginal effect, and to construct a remote sensing image regional network adjustment result accuracy lookup table.

[0075] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described module can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0076] In the technical solution disclosed herein, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0077] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0078] Figure 3 A block diagram of an exemplary electronic device 300 capable of implementing an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0079] The electronic device 300 includes a computing unit 301, which can perform various appropriate actions and processes according to a computer program stored in a ROM 302 or a computer program loaded from a storage unit 308 into a RAM 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 can also be stored. The computing unit 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An I / O interface 305 is also connected to the bus 304.

[0080] A number of components in the electronic device 300 are connected to the I / O interface 305, including: an input unit 306, such as a keyboard, a mouse, etc.; an output unit 307, such as various types of displays, speakers, etc.; a storage unit 308, such as a disk, an optical disk, etc.; and a communication unit 309, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 309 allows the electronic device 300 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0081] The computing unit 301 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 301 performs the various methods and processes described above, such as method 100. For example, in some embodiments, the method 100 may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 308.

[0082] In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 300 via the ROM 302 and / or the communication unit 309. When the computer program is loaded into the RAM 303 and executed by the computing unit 301, one or more steps of the method 100 described above may be performed. Alternatively, in other embodiments, the computing unit 301 may be configured to execute the method 100 in any other appropriate manner (e.g., by means of firmware).

[0083] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0084] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0085] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0086] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0087] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0088] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0089] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0090] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for constructing a remote sensing image block adjustment result accuracy lookup table, characterized in that: include: Obtain the land cover type data and terrain elevation data within the survey area of ​​the remote sensing image regional network adjustment; According to the surface cover type data and the terrain elevation data, the area and proportion of each surface cover type on each terrain type in the survey area of ​​the regional network adjustment are calculated respectively; According to the land cover type data and terrain elevation data, collect enough and evenly distributed test points within the survey area to calculate the accuracy of the sample test points required for the regional network adjustment results of remote sensing images; Design the sequence of the number and location of sample detection points corresponding to each surface coverage type on each terrain type, and calculate the mean error sequence corresponding to each number of sample detection points; Based on the error sequence of sample detection points corresponding to each surface coverage type on each terrain type, the relationship between the accuracy of adjustment results and the area and proportion of terrain and land types, as well as the number and distribution of detection points is statistically analyzed. The minimum number of checkpoints required for accuracy inspection of regional network adjustment results is obtained through marginal effect, and an accuracy lookup table for remote sensing image regional network adjustment results is constructed.

2. The method according to claim 1, characterized in that The designing of a sequence of the number and position of sample detection points corresponding to each surface coverage type on each terrain type, and calculating a mean error sequence corresponding to each number of sample detection points includes: Based on a preset detection point distribution algorithm, the number and location of sample detection points on each surface coverage type on each terrain type are determined according to the area and proportion within the survey area of ​​the regional network adjustment of each surface coverage type on each terrain type, as well as the number and distribution of the detection points; According to the number and position of sample detection points on each surface coverage type on each terrain type, the mean error sequence of the sample detection points corresponding to each surface coverage type on each terrain type is calculated. The mean error sequence of the sample detection points corresponding to each surface coverage type on each terrain type records the mean error information calculated under different strategies in the form of a list.

3. The method according to claim 1, characterized in that The error sequence of sample detection points corresponding to each surface coverage type on each terrain type, the relationship between the accuracy of the adjustment results and the area and proportion of the terrain and land types, as well as the number and distribution of the detection points, the minimum number of checkpoints required for the accuracy check of the regional network adjustment results is obtained through the marginal effect, and the remote sensing image regional network adjustment results accuracy lookup table is constructed, which includes: By using the marginal effect of the mean error of the detection point, a linear fitting is performed on the mean error sequence of the sample detection points corresponding to each surface coverage type on each terrain type, with the number of sample detection points as the horizontal axis and the mean error as the vertical axis, and the stationary point is calculated; wherein the mean error sequence of the sample detection points corresponding to each surface coverage type on each terrain type includes a mean error sequence of a single surface coverage type corresponding to a single terrain type or a mean error sequence of a single terrain type corresponding to a single surface coverage type; According to the station points corresponding to each surface coverage type on each terrain type, the number of sample detection points corresponding to each station point is calculated to obtain the minimum number of checkpoints; The influence weights of terrain type and land cover type are determined according to the number of sample detection points corresponding to each station; According to the influence weight, the area and proportion of the survey area of ​​the remote sensing image regional network adjustment of each surface coverage type on each terrain type, and the number and distribution of the detection points, the corresponding minimum number of detection points is obtained, and the accuracy lookup table of the remote sensing image regional network adjustment results is constructed.

4. The method according to claim 1, characterized in that: The acquisition of land surface coverage type data and terrain elevation data in the survey area for remote sensing image regional block adjustment includes: According to the resolution and accuracy of the adjustment results of the remote sensing image regional network adjustment in the survey area, the initial data of the surface coverage type and the initial data of the terrain elevation in the survey area are obtained; According to the type, resolution and accuracy of the acquired data, the initial data of land cover type and initial data of terrain elevation are sorted in different scales; Rename the sorted initial data of land cover types and initial data of terrain elevation according to preset rules, and store them in the database according to pixel locations to complete the construction of the background library of geographic conditions for regional block adjustment; The surface coverage type data and terrain elevation data within the survey area of ​​the remote sensing image block adjustment are obtained from the block adjustment geographic condition background library.

5. The method according to claim 1, characterized in that The calculating, according to the surface cover type data and the terrain elevation data, the area and proportion of each surface cover type in the survey area of ​​the regional network adjustment on each terrain type includes: According to a preset resolution, the surface cover type data and the terrain elevation data are normalized, wherein the normalization is to construct a complete resolution and precision multi-level continuous regional network adjustment geographic condition background library pyramid data body; According to the normalized surface cover type data and terrain elevation data, the area and proportion of each surface cover type in the survey area of ​​regional network adjustment are calculated respectively.

6. The method according to claim 1, characterized in that The detection points for collecting a sufficient number of evenly distributed sample detection points required for calculating the accuracy of the remote sensing image regional network adjustment results within the measurement area based on the surface cover type data and terrain elevation data include: Based on the preset detection point extraction model, the number and distribution of sample detection points required for the accuracy of the remote sensing image regional network adjustment results are collected and determined; the sample detection points are reliable and sufficient in number.

7. The method according to any one of claims 1 to 6, characterized in that: The land cover type data include cultivated land, forest land, grassland, shrub land, wetland, water body, tundra, artificial surface, bare land, glacier and permanent snow; the terrain elevation data include terrain categories, and the terrain categories include alpine land, mountainous land, hills and plain land.

8. A device for constructing a remote sensing image block adjustment result accuracy lookup table, characterized in that: include: The acquisition module is used to obtain the surface coverage type data and terrain elevation data in the survey area of ​​the remote sensing image regional network adjustment; A processing module, for calculating the area and proportion of each surface cover type on each terrain type in the survey area of ​​the regional network adjustment according to the surface cover type data and the terrain elevation data; The processing module is also used to collect a sufficient number of uniformly distributed detection points within the survey area for calculating the accuracy of the sample detection points required for the remote sensing image regional network adjustment results according to the surface cover type data and the terrain elevation data; The processing module is also used to design a sequence of the number and position of sample detection points corresponding to each surface coverage type on each terrain type, and calculate the mean error sequence corresponding to each number of sample detection points; The generation module is used to calculate the relationship between the accuracy of the adjustment results and the area and proportion of terrain and land types, as well as the number and distribution of the detection points based on the error sequence of the sample detection points corresponding to each surface coverage type on each terrain type. The minimum number of checkpoints required for the accuracy check of the regional network adjustment results is obtained through the marginal effect, and the accuracy lookup table of the remote sensing image regional network adjustment results is constructed.

9. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-7.

Images