Method, device and equipment for identifying invalid values ​​of remote sensing data

Abstract

The present invention provides a method, device, and apparatus for identifying invalid values ​​in remote sensing data, relating to the technical field of remote sensing data analysis. The method comprises: obtaining a first invalid value for remote sensing data from a header file of the remote sensing data; determining a second invalid value for remote sensing data based on the values ​​of multiple bands corresponding to each edge pixel point in the remote sensing data; and determining a target invalid value for the remote sensing data based on the first invalid value for remote sensing data and the second invalid value for remote sensing data. The method of the present invention can accurately determine the invalid value of remote sensing data.

Description

Technical Field

[0001] The present invention relates to the technical field of remote sensing data analysis, and in particular to a method, device and equipment for identifying invalid values ​​of remote sensing data. Background Art

[0002] With the development of national civil and commercial surveying and mapping geographic information satellite remote sensing, the market's spatial raster data tends to have diversified applications.

[0003] Related technologies obtain invalid value information from remote sensing images by reading remote sensing image header files and then render invalid value pixels transparent in remote sensing image visualization. This method has poor accuracy and cannot accurately identify invalid values ​​in remote sensing data. This presents significant technical drawbacks when it comes to visualizing massive amounts of remote sensing data. Summary of the Invention

[0004] The present invention provides a method, device and equipment for identifying invalid values ​​of remote sensing data. First, the invalid value of the first remote sensing data is determined based on the invalid value information in the header file, and then the invalid value of the second remote sensing data is determined based on the values ​​of multiple bands corresponding to edge pixels in the remote sensing data. Finally, by comparing and analyzing the invalid value of the first remote sensing data and the invalid value of the second remote sensing data, the invalid value of the remote sensing data can be accurately determined, thereby effectively improving the accuracy of the invalid value of the remote sensing data.

[0005] The present invention provides a method for identifying invalid values ​​of remote sensing data, comprising the following steps.

[0006] Obtain the first remote sensing data invalid value in the remote sensing data header file;

[0007] Determining an invalid value of the second remote sensing data according to values ​​of multiple bands corresponding to each edge pixel point in the remote sensing data;

[0008] A target invalid value of the remote sensing data is determined according to the first remote sensing data invalid value and the second remote sensing data invalid value.

[0009] According to a method for identifying invalid values ​​of remote sensing data provided by the present invention, determining the invalid value of the second remote sensing data according to the values ​​of multiple bands corresponding to each edge pixel point in the remote sensing data includes:

[0010] According to the values ​​of multiple bands corresponding to each edge pixel point in the remote sensing data, a plurality of sets of homogeneous pixels are obtained; wherein the homogeneous pixel points are pixel points whose values ​​of the multiple bands are all equal;

[0011] The invalid value of the second remote sensing data is determined according to the number of homogeneous pixel points in each of the homogeneous pixel point sets.

[0012] According to a method for identifying invalid values ​​of remote sensing data provided by the present invention, determining the invalid value of the second remote sensing data according to the number of homogeneous pixels in each of the homogeneous pixel sets includes:

[0013] determining a first homogeneous pixel set from the multiple homogeneous pixel sets according to the number of homogeneous pixel points in each of the homogeneous pixel set; the first homogeneous pixel set being the homogeneous pixel set with the largest number of homogeneous pixel points in the multiple homogeneous pixel set;

[0014] A set of values ​​of multiple bands corresponding to the homogeneous pixels in the first homogeneous pixel set is used as an invalid value of the second remote sensing data.

[0015] According to a method for identifying invalid values ​​of remote sensing data provided by the present invention, determining a target invalid value of the remote sensing data based on the invalid value of the first remote sensing data and the invalid value of the second remote sensing data includes:

[0016] In a case where the first remote sensing data invalid value and the second remote sensing data invalid value are the same, determining the first remote sensing data invalid value or the second remote sensing data invalid value as a target invalid value of the remote sensing data;

[0017] When the invalid value of the first remote sensing data is different from the invalid value of the second remote sensing data, the target invalid value of the remote sensing data is determined based on the number of edge pixels corresponding to the invalid value of the first remote sensing data and the number of edge pixels corresponding to the invalid value of the second remote sensing data.

[0018] According to a method for identifying an invalid value of remote sensing data provided by the present invention, when the invalid value of the first remote sensing data and the invalid value of the second remote sensing data are different, determining a target invalid value of the remote sensing data according to the number of edge pixels corresponding to the invalid value of the first remote sensing data and the number of edge pixels corresponding to the invalid value of the second remote sensing data, comprising:

[0019] When the number of edge pixels corresponding to the invalid value of the first remote sensing data is greater than the number of edge pixels corresponding to the invalid value of the second remote sensing data, using the invalid value of the first remote sensing data as the target invalid value of the remote sensing data;

[0020] When the number of edge pixels corresponding to the invalid value of the first remote sensing data is less than the number of edge pixels corresponding to the invalid value of the second remote sensing data, the invalid value of the second remote sensing data is used as the target invalid value of the remote sensing data.

[0021] According to a method for identifying invalid values ​​of remote sensing data provided by the present invention, determining the invalid value of the second remote sensing data according to the values ​​of multiple bands corresponding to each edge pixel point in the remote sensing data includes:

[0022] According to the values ​​of multiple bands corresponding to each pixel point in the edge sliding window of the remote sensing data, the discrete degree of the band value of the pixel point in the edge sliding window is determined;

[0023] When the discrete degree of the band values ​​of the pixel points in the edge sliding window is less than a threshold, the edge sliding window is used as a filtered edge sliding window, and the pixel points in the filtered edge sliding window are used as the edge pixel points.

[0024] According to a method for identifying invalid values ​​of remote sensing data provided by the present invention, when the invalid value of the first remote sensing data is different from the invalid value of the second remote sensing data, and the difference between the number of homogeneous pixels in the first homogeneous pixel set and the number of homogeneous pixels in the second homogeneous pixel set is less than a preset value, the size of the edge sliding window is adjusted and the first homogeneous pixel set is re-determined; the second homogeneous pixel set is any one of the multiple homogeneous pixel sets.

[0025] The present invention also provides a device for identifying invalid values ​​of remote sensing data, comprising the following modules:

[0026] An acquisition module, configured to acquire a first remote sensing data invalid value in a header file of the remote sensing data;

[0027] A determination module, configured to determine an invalid value of the second remote sensing data based on values ​​of multiple bands corresponding to each edge pixel point in the remote sensing data;

[0028] The identification module is configured to determine a target invalid value of the remote sensing data according to the invalid value of the first remote sensing data and the invalid value of the second remote sensing data.

[0029] The present invention also provides an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for identifying invalid values ​​of remote sensing data as described above is implemented.

[0030] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for identifying invalid values ​​of remote sensing data as described above is implemented.

[0031] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above methods for identifying invalid values ​​of remote sensing data.

[0032] The method, device and equipment for identifying invalid values ​​of remote sensing data provided by the present invention first determine the invalid value of the first remote sensing data based on the invalid value information in the header file, and then determine the invalid value of the second remote sensing data based on the values ​​of multiple bands corresponding to edge pixels in the remote sensing data. Finally, by comparing and analyzing the invalid value of the first remote sensing data and the invalid value of the second remote sensing data, the invalid value of the remote sensing data can be accurately determined, thereby effectively improving the accuracy of the invalid value of the remote sensing data. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0034] Figure 1 This is one of the schematic diagrams of the method for identifying invalid values ​​of remote sensing data provided by the present invention.

[0035] Figure 2 It is a schematic diagram of the invalid value identification defect of remote sensing data provided by the present invention.

[0036] Figure 3 This is the second schematic diagram of the method for identifying invalid values ​​of remote sensing data provided by the present invention.

[0037] Figure 4 This is the third schematic diagram of the method for identifying invalid values ​​of remote sensing data provided by the present invention.

[0038] Figure 5 This is the fourth schematic diagram of the method for identifying invalid values ​​of remote sensing data provided by the present invention.

[0039] Figure 6 It is a schematic diagram of the device for identifying invalid values ​​of remote sensing data provided by the present invention.

[0040] Figure 7 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0041] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0042] The following combination Figure 1-Figure 7The present invention describes a method, device and apparatus for identifying invalid values ​​of remote sensing data.

[0043] In order to facilitate a clearer understanding of the technical solutions of the various embodiments of the present application, some technical contents related to the various embodiments of the present application are first introduced.

[0044] like Figure 1 As shown in FIG, in common raster data visualization schemes, invalid value recognition of remote sensing images is achieved by reading invalid value information in the structured data of remote sensing image header files, and invalid value pixels are transparently processed during the remote sensing image visualization process.

[0045] For raster data of varying specifications, it's difficult to achieve optimal visualization results in complex scenarios and massive data applications by simply reading the data header file and automating the visualization of slices. Because invalid values ​​identified in remote sensing image headers differ from actual invalid values, data visualization displays often exhibit noticeable "black edges."

[0046] like Figure 2 As shown, the remote sensing imagery in the figure is composed of a mosaic of two different satellite data sources (gf1: refers to the pixel source being the Gaofen-1 satellite remote sensing imagery, and S2A: refers to the pixel source being the Sentinel L2A-level remote sensing imagery; Null (pro): refers to invalid values ​​specified by a human, machine, or automated program). The invalid values ​​of this data are entirely dependent on the remote sensing image data production unit or producer. In actual production applications, whether it is a professional surveying and mapping geographic information unit, a satellite remote sensing technology unit, or downstream data application related units such as agriculture, mining, and emergency response, there is a vast amount of such data collected due to different project backgrounds and different demand backgrounds. In projects that aggregate related spatial data, the massive amount of complex scenes and raster data from complex sources can make it very difficult to identify invalid values ​​in data visualization. If a single header file reading method is still used to identify invalid raster data values ​​and then publish the visualized data, it is an incorrect representation of this type of data.

[0047] Figure 3 FIG. 1 is a flow chart of a method for identifying invalid values ​​of remote sensing data provided by the present invention, such as Figure 3 As shown, the method includes the following:

[0048] Step 301: Obtain a first remote sensing data invalid value in a header file of remote sensing data.

[0049] Specifically, in the embodiment of the present application, the first remote sensing data invalid value in the remote sensing data header file is first obtained. That is, the invalid raster data value is first identified by reading the header file. For example, if the header file indicates that the remote sensing data invalid value is GRB000, that is, the pixel point with an RGB value of 000 is an invalid value pixel in the remote sensing data, the invalid value pixel can be processed transparently during the remote sensing image visualization process.

[0050] Step 302: Determine an invalid value of the second remote sensing data according to the values ​​of multiple bands corresponding to each edge pixel point in the remote sensing data.

[0051] Specifically, in the embodiment of the present application, after obtaining the invalid value of the first remote sensing data in the header file of the remote sensing data, the invalid value of the second remote sensing data is determined based on the values ​​of the multiple bands corresponding to each edge pixel point in the remote sensing data. Optionally, the invalid values ​​in the remote sensing data are mostly concentrated at the edge of the remote sensing image. In the present application, the invalid value in the second remote sensing data is accurately determined by the values ​​of the multiple bands corresponding to each edge pixel point in the remote sensing data. Optionally, the band combination value with the largest proportion in the edge pixel points can be used as the invalid value of the remote sensing data. For example, if the proportion of edge pixel points with an RGB value of 000 in the edge pixel points is 70%, and the proportion of edge pixel points with an RGB value of 001 in the edge pixel points is 30%, then the invalid value of the second remote sensing data can be determined to be 000. Optionally, the edge pixel points can be circled directly on the remote sensing image, or can be determined by other methods.

[0052] Step 303: Determine a target invalid value of the remote sensing data according to the first remote sensing data invalid value and the second remote sensing data invalid value.

[0053] Specifically, after determining the invalid value of the first remote sensing data and the invalid value of the second remote sensing data, a target invalid value for the remote sensing data can be determined based on the first and second remote sensing data invalid values. For example, if the invalid value of the first remote sensing data is 000 and the invalid value of the second remote sensing data is also 000, that is, the invalid values ​​of the remote sensing data determined by both methods are 000, then the target invalid value for the remote sensing data can be ultimately determined to be 000. Alternatively, if the invalid value of the first remote sensing data is 000 and the invalid value of the second remote sensing data is 001, an alarm message can be output, indicating that the invalid value in the remote sensing data header file may be erroneous and requires further verification. In other words, in the embodiment of the present application, the invalid value of the first remote sensing data is first determined based on the invalid value information in the header file, and then the invalid value of the second remote sensing data is determined based on the values ​​of multiple bands corresponding to edge pixels in the remote sensing data. Finally, by comparing and analyzing the invalid value of the first and second remote sensing data, the invalid value of the remote sensing data can be accurately determined, effectively improving the accuracy of the invalid value of the remote sensing data.

[0054] The method of the above embodiment first determines the invalid value of the first remote sensing data based on the invalid value information in the header file, and then determines the invalid value of the second remote sensing data based on the values ​​of multiple bands corresponding to the edge pixels in the remote sensing data. Finally, by comparing and analyzing the invalid value of the first remote sensing data and the invalid value of the second remote sensing data, the invalid value of the remote sensing data can be accurately determined, thereby effectively improving the accuracy of the invalid value of the remote sensing data.

[0055] In one embodiment, determining the invalid value of the second remote sensing data according to the values ​​of multiple bands corresponding to each edge pixel point in the remote sensing data includes:

[0056] According to the values ​​of multiple bands corresponding to each edge pixel in the remote sensing data, multiple sets of homogeneous pixels are obtained; wherein the homogeneous pixels are pixels with equal values ​​in multiple bands;

[0057] The invalid value of the second remote sensing data is determined according to the number of homogeneous pixel points in each homogeneous pixel point set.

[0058] Specifically, in an embodiment of the present application, multiple sets of homogeneous pixels are first obtained based on the values ​​of multiple bands corresponding to each edge pixel in the remote sensing data; wherein, homogeneous pixels are pixels with equal values ​​in multiple bands. For example, if the RGB values ​​of the three bands corresponding to edge pixel 1 and edge pixel 2 are 000, then edge pixel 1 and edge pixel 2 can be combined into homogeneous pixel set 1. If the RGB values ​​of the three bands corresponding to edge pixel 2, edge pixel 3, and edge pixel 4 are all 001, then edge pixel 2, edge pixel 3, and edge pixel 4 can be combined into homogeneous pixel set 2.

[0059] Optionally, multiple homogeneous pixel sets are obtained based on the values ​​of multiple bands corresponding to each edge pixel in the remote sensing data, and the invalid value of the second remote sensing data can be determined based on the number of homogeneous pixels in each homogeneous pixel set. Optionally, the number of homogeneous pixels in homogeneous pixel set 2 is 3, and the number of homogeneous pixels in homogeneous pixel set 1 is 2. That is, there are more pixels with an RGB value of 001 than pixels with an RGB value of 000 among the edge pixels. In this case, the RGB value of 001 can be determined as an invalid value for the remote sensing data.

[0060] The method of the above embodiment obtains multiple homogeneous pixel point sets based on the values ​​of multiple bands corresponding to each edge pixel point in the remote sensing data, that is, the edge pixel points are classified according to the values ​​of multiple bands corresponding to each edge pixel point to obtain multiple homogeneous pixel point sets; and then, based on the number of homogeneous pixel points in each homogeneous pixel point set, the invalid value of the second remote sensing data can be accurately determined. Further, by comparing and analyzing the invalid value of the first remote sensing data and the invalid value of the second remote sensing data, the invalid value of the remote sensing data can be finally and accurately determined, thereby effectively improving the accuracy of the invalid value of the remote sensing data.

[0061] In some embodiments, determining the invalid value of the second remote sensing data according to the number of homogeneous pixel points in each homogeneous pixel point set includes:

[0062] Determining a first homogeneous pixel point set from the multiple homogeneous pixel point sets according to the number of homogeneous pixel points in each homogeneous pixel point set; the first homogeneous pixel point set is the homogeneous pixel point set with the largest number of homogeneous pixel points in the multiple homogeneous pixel point sets;

[0063] A set of values ​​of multiple bands corresponding to the homogeneous pixels in the first homogeneous pixel set is used as the second remote sensing data invalid value.

[0064] Specifically, after classifying edge pixels according to the values ​​of multiple bands corresponding to each edge pixel to obtain multiple homogeneous pixel sets, the embodiment of the present application further determines a first homogeneous pixel set from the multiple homogeneous pixel sets based on the number of homogeneous pixels in each homogeneous pixel set; wherein the first homogeneous pixel set is the homogeneous pixel set with the largest number of homogeneous pixels among the multiple homogeneous pixel sets. For example, if there are 100 pixels with an RGB value of 000 in homogeneous pixel set A and 200 pixels with an RGB value of 001 in homogeneous pixel set B, then homogeneous pixel set B can be determined to be the first homogeneous pixel set. Optionally, the number of pixels in the homogeneous pixel set A and the homogeneous pixel set B can be sorted to determine whether there are more homogeneous pixels with RGB values ​​of 000 in the homogeneous pixel set A or more homogeneous pixels with RGB values ​​of 001 in the homogeneous pixel set B, thereby accurately determining the first homogeneous pixel set from the homogeneous pixel set A and the homogeneous pixel set B.

[0065] Optionally, after determining the first homogeneous pixel set, the set of values ​​of multiple bands corresponding to the homogeneous pixels in the first homogeneous pixel set can be used as the second remote sensing data invalid value. For example, after determining that homogeneous pixel set B is the first homogeneous pixel set, the set of values ​​of multiple bands corresponding to the homogeneous pixels in homogeneous pixel set B, RGB001, can be used as the second remote sensing data invalid value.

[0066] The method of the above embodiment determines a first homogeneous pixel point set from multiple homogeneous pixel point sets based on the number of homogeneous pixel points in each homogeneous pixel point set. That is, after determining the homogeneous pixel point set with the largest number of homogeneous pixel points from multiple homogeneous pixel point sets as the first homogeneous pixel point set, the set of multiple band values ​​corresponding to the homogeneous pixels in the first homogeneous pixel point set can be used as the invalid value of the second remote sensing data, thereby realizing accurate and rapid determination of the invalid value of the second remote sensing data.

[0067] In one embodiment, determining a target invalid value of remote sensing data according to the first remote sensing data invalid value and the second remote sensing data invalid value includes:

[0068] In a case where the first remote sensing data invalid value and the second remote sensing data invalid value are the same, determining the first remote sensing data invalid value or the second remote sensing data invalid value as a target invalid value of the remote sensing data;

[0069] When the first remote sensing data invalid value and the second remote sensing data invalid value are different, the target invalid value of the remote sensing data is determined according to the number of edge pixels corresponding to the first remote sensing data invalid value and the number of edge pixels corresponding to the second remote sensing data invalid value.

[0070] Specifically, in an embodiment of the present application, when the invalid value of the first remote sensing data and the invalid value of the second remote sensing data are the same, the invalid value of the first remote sensing data or the invalid value of the second remote sensing data is determined as the target invalid value of the remote sensing data. For example, when the invalid value of the first remote sensing data is RGB000 and the invalid value of the second remote sensing data is also RGB000, the target invalid value of the remote sensing data is determined to be RGB000.

[0071] Optionally, when the first remote sensing data invalid value and the second remote sensing data invalid value are different, the target invalid value of the remote sensing data is determined based on the number of edge pixels corresponding to the first remote sensing data invalid value and the number of edge pixels corresponding to the second remote sensing data invalid value. Optionally, when the number of edge pixels corresponding to the first remote sensing data invalid value is greater than the number of edge pixels corresponding to the second remote sensing data invalid value, the first remote sensing data invalid value is used as the target invalid value of the remote sensing data. When the number of edge pixels corresponding to the first remote sensing data invalid value is less than the number of edge pixels corresponding to the second remote sensing data invalid value, the second remote sensing data invalid value is used as the target invalid value of the remote sensing data. For example, when the number of edge pixels corresponding to the first remote sensing data invalid value RGB000 is 100 and the number of edge pixels corresponding to the second remote sensing data invalid value RGB001 is 200, the target invalid value of the remote sensing data is determined to be RGB001.

[0072] The method of the above embodiment determines the first remote sensing data invalid value or the second remote sensing data invalid value as the target invalid value of the remote sensing data when the first remote sensing data invalid value and the second remote sensing data invalid value are the same; when the first remote sensing data invalid value and the second remote sensing data invalid value are different, the target invalid value of the remote sensing data is determined according to the number of edge pixel points corresponding to the first remote sensing data invalid value and the number of edge pixel points corresponding to the second remote sensing data invalid value, thereby achieving accurate determination of the target invalid value of the remote sensing data in different scenarios and different situations, effectively improving the accuracy of the remote sensing data invalid value.

[0073] In some embodiments, determining the invalid value of the second remote sensing data based on the values ​​of multiple bands corresponding to each edge pixel point in the remote sensing data includes:

[0074] According to the values ​​of multiple bands corresponding to each pixel point in the edge sliding window of the remote sensing data, the discrete degree of the band value of the pixel point in the edge sliding window is determined;

[0075] When the discrete degree of the band value of the pixel point in the edge sliding window is less than the threshold, the edge sliding window is used as the filtered edge sliding window, and the pixel point in the filtered edge sliding window is used as the edge pixel point.

[0076] Specifically, in an embodiment of the present application, the size of the edge sliding window of the remote sensing data and the step size of the edge sliding window can be first determined, and then the edge pixel points of the remote sensing data can be traversed through the edge sliding window of the remote sensing data. Then, based on the values ​​of the multiple bands corresponding to each pixel point in the edge sliding window of the remote sensing data, the discrete degree of the band value of the pixel point in the edge sliding window is determined. For example, in the case where the edge sliding window contains multiple pixels, such as the RGB value of pixel point 1 is 000, the RGB value of pixel point 2 is 001, and the RGB value of pixel point 3 is 111, the discrete degree of the band value of the pixel point in the edge sliding window can be calculated based on the values ​​of the multiple bands corresponding to the multiple pixels in the edge sliding window. Optionally, the discrete degree of the band value of the pixel point in the edge sliding window can be characterized by the variance or standard deviation of the multiple band values ​​of the multiple pixels.

[0077] Optionally, if the degree of dispersion of the band values ​​of the pixels within the edge sliding window is less than a threshold, it indicates that the degree of dispersion of the band values ​​of the pixels within the sliding window is small. In this case, the edge sliding window can be used as a filtered edge sliding window, and the pixels within the filtered edge sliding window can be used as edge pixels to determine the invalid value of the second remote sensing data. This makes the determined invalid value of the second remote sensing data more accurate, effectively improving the accuracy of the invalid value of the remote sensing data. Optionally, if the degree of dispersion of the band values ​​of the pixels within the edge sliding window is greater than a threshold, the pixels within the edge sliding window are discarded, that is, they are no longer used as sample data for calculating the second remote sensing data, thereby improving the accuracy of the invalid value of the remote sensing data.

[0078] In the method of the above embodiment, when the discrete degree of the band value of the pixel point in the edge sliding window is less than the threshold value, it indicates that the discrete degree of the band value of the pixel point in the sliding window is small, and the edge sliding window can be used as the filtered edge sliding window, and the pixel points in the filtered edge sliding window can be used as edge pixel points, so as to determine the invalid value of the second remote sensing data, thereby effectively improving the accuracy of the invalid value of the remote sensing data.

[0079] In one embodiment, when the invalid value of the first remote sensing data is different from the invalid value of the second remote sensing data, and the difference between the number of homogeneous pixels in the first homogeneous pixel set and the number of homogeneous pixels in the second homogeneous pixel set is less than a preset value, the size of the edge sliding window is adjusted and the first homogeneous pixel set is re-determined; the second homogeneous pixel set is any one of the multiple homogeneous pixel sets.

[0080] Specifically, when the difference between the number of homogeneous pixels in the first homogeneous pixel set and the number of homogeneous pixels in the second homogeneous pixel set is less than a preset value, it indicates that the statistical result is not representative enough. Therefore, the first homogeneous pixel set can be re-determined by expanding the size of the edge sliding window, thereby effectively improving the accuracy of the invalid value of the remote sensing data.

[0081] In the method of the above embodiment, when the difference between the number of homogeneous pixels in the first homogeneous pixel set and the number of homogeneous pixels in the second homogeneous pixel set is less than a preset value, the first homogeneous pixel set is re-determined by expanding the size of the edge sliding window, thereby effectively improving the accuracy of the invalid value of the remote sensing data.

[0082] For example, Figure 4 As shown, the embodiment of the present application provides a method for identifying invalid values ​​of remote sensing data, which is as follows:

[0083] (1) Data acquisition & header file reading.

[0084] First, obtain the raster data and read the header file of the raster data to obtain the invalid value of the raster data.

[0085] (2) Edge sliding window traversal & variance and standard deviation calculation.

[0086] Edge sliding window traversal automatically selects several long borders along the edges of the spatial raster data for subsequent calculations. Optionally, the sliding window should be uniform to ensure that the traversed sliding window blocks effectively represent the effective distribution of pixel values ​​at the edge of the raster data. After selecting the sliding window blocks, the variance and standard deviation within each sliding window block are calculated to examine the differences in pixel value distribution within the blocks.

[0087] (3) Sliding window sample screening and homogeneous pixel count comparison.

[0088] After completing the edge sliding window traversal and calculating the variance and standard deviation of the pixel values ​​within the sliding window block, the sliding window block with the maximum and minimum extreme values ​​of the variance and standard deviation and a fixed range above and below the median should be selected as the sliding window sample. After the sliding window sample is screened, the homogeneous pixel count comparison is performed. During the homogeneous pixel count comparison stage, the pixel values ​​of different bands should be cumulatively counted for all bands within the sliding window sample. After completion, the pixel value with the highest count is selected to represent the invalid value of the count statistics.

[0089] (4) Compare invalid value counts and identify invalid values.

[0090] like Figure 5 As shown in FIG, if the "header invalid value" and the "count statistics invalid value" are the same, the "header invalid value" or the "count statistics invalid value" is determined as the final invalid value of the remote sensing data. If the "header invalid value" and the "count statistics invalid value" are different, the target invalid value of the remote sensing data is determined based on the number of edge pixels corresponding to the "header invalid value" and the number of edge pixels corresponding to the "count statistics invalid value".

[0091] The method of the above embodiment realizes accurate identification of invalid values ​​assisted by data visualization (slicing or slicing-free) of massive multi-source remote sensing data in complex scenarios, and realizes identification of invalid values ​​in remote sensing data with high universality.

[0092] The following describes the identification device for remote sensing data invalid values ​​provided by the present invention. The identification device for remote sensing data invalid values ​​described below and the identification method for remote sensing data invalid values ​​described above can be referred to each other. Figure 6 Shown, including:

[0093] An acquisition module 610 is configured to acquire a first remote sensing data invalid value in a header file of the remote sensing data;

[0094] A determination module 620 is configured to determine an invalid value of the second remote sensing data based on values ​​of multiple bands corresponding to each edge pixel point in the remote sensing data;

[0095] The identification module 630 is configured to determine a target invalid value of the remote sensing data according to the first remote sensing data invalid value and the second remote sensing data invalid value.

[0096] Optionally, the determining module 620 is specifically configured to: obtain a plurality of sets of homogeneous pixels according to the values ​​of the plurality of bands corresponding to each edge pixel in the remote sensing data; wherein the homogeneous pixels are pixels having the same values ​​in the plurality of bands;

[0097] The invalid value of the second remote sensing data is determined according to the number of homogeneous pixel points in each homogeneous pixel point set.

[0098] Optionally, the determining module 620 is specifically configured to:

[0099] Determining a first homogeneous pixel point set from the multiple homogeneous pixel point sets according to the number of homogeneous pixel points in each homogeneous pixel point set; the first homogeneous pixel point set is the homogeneous pixel point set with the largest number of homogeneous pixel points in the multiple homogeneous pixel point sets;

[0100] A set of values ​​of multiple bands corresponding to the homogeneous pixels in the first homogeneous pixel set is used as the second remote sensing data invalid value.

[0101] Optionally, the identification module 630 is specifically configured to:

[0102] In a case where the first remote sensing data invalid value and the second remote sensing data invalid value are the same, determining the first remote sensing data invalid value or the second remote sensing data invalid value as a target invalid value of the remote sensing data;

[0103] When the first remote sensing data invalid value and the second remote sensing data invalid value are different, the target invalid value of the remote sensing data is determined according to the number of edge pixels corresponding to the first remote sensing data invalid value and the number of edge pixels corresponding to the second remote sensing data invalid value.

[0104] Optionally, the identification module 630 is specifically configured to:

[0105] When the number of edge pixel points corresponding to the invalid value of the first remote sensing data is greater than the number of edge pixel points corresponding to the invalid value of the second remote sensing data, the invalid value of the first remote sensing data is used as the target invalid value of the remote sensing data;

[0106] When the number of edge pixels corresponding to the invalid value of the first remote sensing data is less than the number of edge pixels corresponding to the invalid value of the second remote sensing data, the invalid value of the second remote sensing data is used as the target invalid value of the remote sensing data.

[0107] Optionally, the determining module 620 is further configured to:

[0108] According to the values ​​of multiple bands corresponding to each pixel point in the edge sliding window of the remote sensing data, the discrete degree of the band value of the pixel point in the edge sliding window is determined;

[0109] When the discrete degree of the band value of the pixel point in the edge sliding window is less than the threshold, the edge sliding window is used as the filtered edge sliding window, and the pixel point in the filtered edge sliding window is used as the edge pixel point.

[0110] Optionally, the determining module 620 is further configured to:

[0111] When the invalid value of the first remote sensing data is different from the invalid value of the second remote sensing data, and the difference between the number of homogeneous pixels in the first homogeneous pixel set and the number of homogeneous pixels in the second homogeneous pixel set is less than a preset value, the size of the edge sliding window is adjusted and the first homogeneous pixel set is re-determined; the second homogeneous pixel set is any one of the multiple homogeneous pixel sets.

[0112] Figure 7 The present invention provides an example of a physical structure diagram of an electronic device, which may include: a processor 710, a communications interface 720, a memory 730, and a communications bus 740. The processor 710, the communications interface 720, and the memory 730 communicate with each other via the communications bus 740. The processor 710 may invoke logic instructions in the memory 730 to execute a method for identifying invalid values ​​in remote sensing data. The method includes: obtaining a first invalid value for remote sensing data from a header file of the remote sensing data; determining a second invalid value for remote sensing data based on values ​​of multiple bands corresponding to edge pixels in the remote sensing data; and determining a target invalid value for the remote sensing data based on the first invalid value for remote sensing data and the second invalid value for remote sensing data.

[0113] Furthermore, the logic instructions in the aforementioned memory 730 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product, stored in a storage medium, includes instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0114] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the method for identifying invalid values ​​of remote sensing data provided by the above methods, the method including: obtaining a first invalid value of remote sensing data in a header file of the remote sensing data; determining a second invalid value of remote sensing data based on the values ​​of multiple bands corresponding to each edge pixel point in the remote sensing data; and determining a target invalid value of the remote sensing data based on the first invalid value of remote sensing data and the second invalid value of remote sensing data.

[0115] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it is implemented to execute the method for identifying invalid values ​​of remote sensing data provided by the above methods. The method includes: obtaining a first invalid value of remote sensing data in a header file of the remote sensing data; determining a second invalid value of remote sensing data based on the values ​​of multiple bands corresponding to each edge pixel point in the remote sensing data; and determining a target invalid value of the remote sensing data based on the first invalid value of remote sensing data and the second invalid value of remote sensing data.

[0116] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0117] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0118] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for identifying invalid values ​​of remote sensing data, characterized in that: include: Obtain the first remote sensing data invalid value in the remote sensing data header file; Determining an invalid value of the second remote sensing data according to values ​​of multiple bands corresponding to each edge pixel point in the remote sensing data; determining a target invalid value of the remote sensing data according to the first remote sensing data invalid value and the second remote sensing data invalid value; The method further comprises: According to the values ​​of multiple bands corresponding to each pixel point in the edge sliding window of the remote sensing data, the discrete degree of the band value of the pixel point in the edge sliding window is determined; When the discrete degree of the band values ​​of the pixel points in the edge sliding window is less than a threshold, the edge sliding window is used as a filtered edge sliding window, and the pixel points in the filtered edge sliding window are used as the edge pixel points.

2. The method for identifying invalid values ​​of remote sensing data according to claim 1, characterized in that: The determining of the invalid value of the second remote sensing data according to the values ​​of the multiple bands corresponding to each edge pixel point in the remote sensing data includes: According to the values ​​of multiple bands corresponding to each edge pixel point in the remote sensing data, a plurality of homogeneous pixel point sets are obtained; wherein the homogeneous pixel points are pixel points whose values ​​of the multiple bands are all equal; The invalid value of the second remote sensing data is determined according to the number of homogeneous pixel points in each of the homogeneous pixel point sets.

3. The method for identifying invalid values ​​of remote sensing data according to claim 2, characterized in that: The determining, according to the number of homogeneous pixel points in each of the homogeneous pixel point sets, the invalid value of the second remote sensing data includes: determining a first homogeneous pixel set from the multiple homogeneous pixel sets according to the number of homogeneous pixel points in each of the homogeneous pixel set; the first homogeneous pixel set being the homogeneous pixel set with the largest number of homogeneous pixel points in the multiple homogeneous pixel set; A set of values ​​of multiple bands corresponding to the homogeneous pixels in the first homogeneous pixel set is used as an invalid value of the second remote sensing data.

4. The method for identifying invalid values ​​of remote sensing data according to any one of claims 1 to 3, characterized in that: The step of determining a target invalid value of the remote sensing data according to the first remote sensing data invalid value and the second remote sensing data invalid value includes: In a case where the first remote sensing data invalid value and the second remote sensing data invalid value are the same, determining the first remote sensing data invalid value or the second remote sensing data invalid value as a target invalid value of the remote sensing data; When the invalid value of the first remote sensing data is different from the invalid value of the second remote sensing data, the target invalid value of the remote sensing data is determined based on the number of edge pixels corresponding to the invalid value of the first remote sensing data and the number of edge pixels corresponding to the invalid value of the second remote sensing data.

5. The method for identifying invalid values ​​of remote sensing data according to claim 4, characterized in that: The method further comprises: determining a target invalid value of the remote sensing data according to a number of edge pixels corresponding to the invalid value of the first remote sensing data and a number of edge pixels corresponding to the invalid value of the second remote sensing data when the invalid value of the first remote sensing data is different from the invalid value of the second remote sensing data, including: When the number of edge pixels corresponding to the invalid value of the first remote sensing data is greater than the number of edge pixels corresponding to the invalid value of the second remote sensing data, using the invalid value of the first remote sensing data as the target invalid value of the remote sensing data; When the number of edge pixels corresponding to the invalid value of the first remote sensing data is less than the number of edge pixels corresponding to the invalid value of the second remote sensing data, the invalid value of the second remote sensing data is used as the target invalid value of the remote sensing data.

6. The method for identifying invalid values ​​of remote sensing data according to claim 3, characterized in that: The method further comprises: When the invalid value of the first remote sensing data is different from the invalid value of the second remote sensing data, and the difference between the number of homogeneous pixels in the first homogeneous pixel set and the number of homogeneous pixels in the second homogeneous pixel set is less than a preset value, the size of the edge sliding window is adjusted and the first homogeneous pixel set is re-determined; the second homogeneous pixel set is any one of the multiple homogeneous pixel sets.

7. A device for identifying invalid values ​​of remote sensing data, characterized in that: include: An acquisition module, configured to acquire a first remote sensing data invalid value in a header file of the remote sensing data; A determination module, configured to determine an invalid value of the second remote sensing data based on values ​​of multiple bands corresponding to each edge pixel point in the remote sensing data; an identification module, configured to determine a target invalid value of the remote sensing data according to the invalid value of the first remote sensing data and the invalid value of the second remote sensing data; The determining module is further configured to: According to the values ​​of multiple bands corresponding to each pixel point in the edge sliding window of the remote sensing data, the discrete degree of the band value of the pixel point in the edge sliding window is determined; When the discrete degree of the band values ​​of the pixel points in the edge sliding window is less than a threshold, the edge sliding window is used as a filtered edge sliding window, and the pixel points in the filtered edge sliding window are used as the edge pixel points.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for identifying invalid values ​​of remote sensing data according to any one of claims 1 to 6 is implemented.

Images