Normalized vegetation index filling method and device, equipment and medium

Abstract

The invention discloses a normalized vegetation index filling method, device, equipment and medium, and relates to the field of data processing of satellites or aerial image.The normalized vegetation index filling method comprises the steps that according to a second time sequence data set of a target area, multi-temporal segmentation is conducted on the target area, and all homogeneous areas of the target area are determined; performing numerical correction on the first time sequence data set corresponding to each homogeneous region according to the image data of each homogeneous region in the first time sequence data set of the target region and the second time sequence data set; wherein each pixel in the image data of the first time sequence data set and the second time sequence data set corresponds to a normalized vegetation index; the spatial resolution of the first time sequence data set is smaller than that of the second time sequence data set; and based on the corrected first time sequence data set, performing missing value filling on missing image data in the second time sequence data set to obtain a second time sequence data set after missing value filling.

Description

Technical Field

[0001] The present invention relates to the field of satellite or aerial image data processing, and in particular to a method, device, equipment and medium for filling a normalized vegetation index. Background Art

[0002] High-resolution Normalized Difference Vegetation Index (NDVI) time series data are crucial for supporting decision-making in areas such as surface vegetation monitoring, agricultural management practices, climate change research, disaster warning, and land use change mapping. In agricultural engineering, in particular, the spatiotemporal continuity of NDVI data significantly impacts crop yield prediction and farmland resource management efficiency. While existing NDVI products generated by the Moderate Resolution Imaging Spectroradiometer (MODIS) have an 8-day temporal resolution, their low spatial resolution makes it difficult to capture surface details, limiting their application in heterogeneous regions. While moderate-resolution satellite data, such as Sentinel-2, improve the spatiotemporal resolution of surface observations, they still suffer from significant data gaps in heterogeneous landscapes characterized by high cloud density and complex terrain.

[0003] Therefore, how to fill the missing values ​​of high-resolution normalized difference vegetation index time series data has become a technical problem that needs to be solved urgently by those skilled in the art. Summary of the Invention

[0004] The object of the present invention is to provide a method, device, equipment and medium for filling the normalized vegetation index, so as to fill the missing values ​​of high-resolution normalized vegetation index time series data.

[0005] In order to achieve the above object, the present invention provides the following technical solutions: A method for filling a normalized vegetation index includes: performing multi-temporal segmentation on the target area based on a second time series data set of the target area to determine each homogeneous area of ​​the target area; performing numerical correction on the first time series data set corresponding to each homogeneous area based on the image data of each homogeneous area in the first time series data set of the target area and the second time series data set to obtain a first time series data set after numerical correction; wherein each pixel in the image data of the first time series data set and the second time series data set corresponds to a normalized vegetation index; the spatial resolution of each image data of the first time series data set is greater than the spatial resolution of each image data of the second time series data set; based on the corrected first time series data set, filling missing values ​​of the missing image data in the second time series data set to obtain a second time series data set after missing value filling.

[0006] In an optional embodiment of the present application, the target area is segmented into multiple temporal phases based on the second time series data set of the target area to determine the various homogeneous areas of the target area, including: using a simple non-iterative clustering algorithm, combining the spatial distribution of the image data of the second time series data set in the target area and the temporal distribution between different image data, to perform multi-temporal segmentation on the target area to determine the various homogeneous areas of the target area.

[0007] In an optional embodiment of the present application, based on the image data of each homogeneous area in the first time series data set of the target area and the second time series data set, the first time series data set corresponding to each homogeneous area is numerically corrected to obtain a numerically corrected first time series data set, including: updating the image data in the first time series data set based on the median of the difference between each image data of the first time series data set in the homogeneous area to obtain an updated first time series data set; and numerically correcting the updated first time series data set based on the second time series data set to obtain a numerically corrected first time series data set.

[0008] In an optional embodiment of the present application, the image data in the first time series data set is updated based on the median of the difference between each image data in the first time series data set in the homogeneous area to obtain an updated first time series data set, including: for any of the homogeneous areas, taking the image data in the first time series data set corresponding to the homogeneous area as the reference data; determining the first update data based on the median of the difference between the image data in the second time series data set and the reference data; updating the image data in the second time series data set based on the first update data and the reference data; determining the second update data based on the median of the difference between the image data in the third time series data set and the image data ranked second in the first time series data set; updating the image data ranked third in the first time series data set based on the first update data, the second update data and the reference data; and so on, until each image data in the first time series data set is traversed to obtain an updated first time series data set.

[0009] In an optional implementation manner of the present application, the image data in the first time series data set is updated using the following formula to obtain an updated first time series data set: ; ; in, represents the nth image data in the first time series data set after update, where n is an integer greater than or equal to 2; represents the image data with the first time sequence in the first time series data set; represents the image data ranked at the i-th position in the first time series data set; represents the median of the difference between the normalized vegetation index of each image data ranked at the i-th position and each image data ranked at the i-1th position in the first time series data set in the homogeneous area; Indicates the updated image data of the first time series dataset at coordinates The normalized vegetation index sequence corresponding to the pixels.

[0010] In an optional embodiment of the present application, the updated first time series data set is numerically corrected based on the second time series data set to obtain the numerically corrected first time series data set, including: taking each image data in the second time series data set as the target, using a linear transfer function to numerically correct each image data in the first time series data set to obtain the corrected first time series data set.

[0011] In an optional implementation of the present application, the updated first time series data is numerically corrected using the following formula to obtain a numerically corrected first time series data set: ; in, Indicates the coordinates of each image data in the second time series data set The normalized vegetation index sequence corresponding to the pixels; and Indicates that the first time series dataset after update is at coordinate Correction coefficient of the normalized vegetation index of the pixel; and By minimizing the corrected first time series data set and The difference between them is obtained; Indicates the updated image data of the first time series dataset at coordinates The normalized vegetation index sequence corresponding to the pixels.

[0012] Compared with the prior art, the method for filling the normalized vegetation index provided by the present invention performs multi-temporal segmentation on the second time series data set of the target area to obtain various homogeneous areas of the target area, and uses the homogeneous unit as the correction unit, and numerically corrects the first time series data set whose spatial resolution of the target area is smaller than that of the second time series data set in combination with the second time series data set, and fills the missing values ​​of the missing image data in the second time series data set based on the numerically corrected first time series data set. This method divides the target area by performing multi-temporal segmentation on the target area in combination with the second time series data set, taking into account the spatial distribution and temporal distribution of the normalized vegetation index. This helps to improve the data quality of the corrected first time series data set in combination with the spatial distribution and temporal distribution of the normalized vegetation index during the process of numerically correcting the first time series data set, and improves the data quality of the second time series data set after the missing values ​​are filled.

[0013] The present invention also provides a normalized vegetation index filling device, comprising: The time phase segmentation unit is used to perform multi-time phase segmentation on the target area according to the second time series data set of the target area, and determine each homogeneous area of ​​the target area.

[0014] A numerical correction unit is used to numerically correct the image data of each homogeneous area in the first time series data set of the target area to obtain a numerically corrected first time series data set; wherein each pixel in the image data of the first time series data set and the second time series data set corresponds to a normalized vegetation index; the spatial resolution of each image data of the first time series data set is greater than the spatial resolution of each image data of the second time series data set.

[0015] The value filling unit is used to fill missing values ​​of the missing image data in the second time series data set based on the corrected first time series data set to obtain the second time series data set after the missing values ​​are filled.

[0016] Compared with the prior art, the beneficial effects of the normalized vegetation index filling device provided by the present invention are the same as the beneficial effects of the normalized vegetation index filling method described in the above technical solution, and are not described in detail here.

[0017] The present invention further provides an electronic device, comprising: processor.

[0018] A memory for storing instructions executable by the processor.

[0019] The processor is configured to execute the above-mentioned normalized vegetation index filling method by running instructions in the memory.

[0020] Compared with the prior art, the beneficial effects of the electronic device provided by the present invention are the same as the beneficial effects of the method for filling the normalized vegetation index described in the above technical solution, and will not be described in detail here.

[0021] The present invention also provides a computer storage medium, in which instructions are stored. When the instructions are executed, the above-mentioned method for filling the normalized vegetation index is implemented.

[0022] Compared with the prior art, the beneficial effects of the computer storage medium provided by the present invention are the same as the beneficial effects of the method for filling the normalized vegetation index described in the above technical solution, and will not be described in detail here. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings: Figure 1 This is a flow chart of the method for filling the normalized vegetation index provided in an embodiment of the present application.

[0024] Figure 2 A schematic diagram of a homogeneous region of a target region provided in an embodiment of the present application.

[0025] Figure 3 The data curve provided for the embodiment of this application Figure 1 .

[0026] Figure 4 The data curve provided for the embodiment of this application Figure 2 .

[0027] Figure 5 The data curve provided for the embodiment of this application Figure 3 .

[0028] Figure 6 This is a structural diagram of the normalized vegetation index filling device provided in an embodiment of the present application.

[0029] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0030] To facilitate a clear description of the technical solutions of the embodiments of the present invention, the words "first" and "second" are used in the embodiments of the present invention to distinguish between identical or similar items with substantially the same functions and effects. For example, the first threshold and the second threshold are merely used to distinguish between different thresholds and do not limit their order. Those skilled in the art will understand that the words "first" and "second" do not limit the quantity or execution order, and the words "first" and "second" do not necessarily mean different.

[0031] It should be noted that, in the present invention, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the present invention should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0032] In the present invention, "at least one" means one or more, and "more" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: the existence of A alone, the existence of A and B at the same time, and the existence of B alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, the combination of a and b, the combination of a and c, the combination of b and c, or the combination of a, b and c, where a, b, c can be single or plural.

[0033] High-resolution Normalized Difference Vegetation Index (NDVI) time series data are crucial for supporting decision-making in areas such as surface vegetation monitoring, agricultural management practices, climate change research, disaster warning, and land use change mapping. In agricultural engineering, in particular, the spatiotemporal continuity of NDVI data significantly impacts crop yield prediction and farmland resource management efficiency. While existing NDVI products generated by the Moderate Resolution Imaging Spectroradiometer (MODIS) have an 8-day temporal resolution, their low spatial resolution makes it difficult to capture surface details, limiting their application in heterogeneous regions. While moderate-resolution satellite data, such as Sentinel-2, improve the spatiotemporal resolution of surface observations, they still suffer from significant data gaps in heterogeneous landscapes characterized by high cloud density and complex terrain.

[0034] How to fill the missing values ​​of high-resolution normalized difference vegetation index time series data has become a technical problem that needs to be solved urgently by those skilled in the art.

[0035] In order to solve the above technical problems, the present application provides a method, device, equipment and medium for filling the normalized vegetation index, which are described in detail one by one in the following embodiments.

[0036] This application embodiment first provides a method for filling the normalized vegetation index, please refer to Figure 1 , Figure 1 This is a flow chart of the method for filling the normalized vegetation index provided in an embodiment of the present application.

[0037] like Figure 1 As shown, the method for filling the normalized vegetation index includes the following S101 to S103.

[0038] S101 , performing multi-temporal segmentation on the target region according to a second time series data set of the target region to determine homogeneous regions of the target region.

[0039] The second time series data set refers to a preprocessed Normalized Difference Vegetation Index (NDVI) covering the target area. In actual application, the second time series data set includes multiple image data sorted by shooting time, and each pixel in the image data corresponds to an NDVI at the pixel position.

[0040] NDVI is a widely used indicator in remote sensing to assess vegetation growth and coverage. It is calculated using reflectance data from the near-infrared (NIR) and red bands of satellite or aerial imagery.

[0041] The purpose of the normalized vegetation index filling method provided in the embodiment of the present application is to solve the problem of discontinuous NDVI data due to the spatiotemporal discontinuity of optical images in cloudy weather, and to improve the accuracy and efficiency of NDVI reconstruction in complex terrain and heterogeneous landscape areas. Its core idea is to fill in NDVI data with high spatial resolution but spatiotemporal discontinuity of optical images, thereby solving the above technical problems.

[0042] In the process of actual application, it is beneficial to have a good spatial resolution of medium-resolution satellites. Therefore, in an optional embodiment of the present application, the second time series data set can use a series of image data collected by the Sentinel-2 satellite, and perform band feature extraction on the near-infrared band and red band of the image data to obtain NDVI data. Specifically, the spatial resolution of the Sentinel-2 satellite is 10 meters, and the temporal resolution is 5 to 10 days. However, considering that in heterogeneous landscape areas with more clouds and complex terrain, the NDVI collected by the Sentinel-2 satellite still has data missing problems. Therefore, it is necessary to fill in the NDVI data.

[0043] Considering that the image data collected by the Sentinel-2 satellite may have different time intervals, before performing multi-temporal segmentation on the target area, the second time series dataset collected by the Sentinel-2 satellite can also be declouded and repaired to improve the quality of the second time series dataset.

[0044] Specifically, the process of declouding and repairing the second time series dataset includes: based on a pre-trained machine learning model, combining multispectral features to decloud each image data in the second time series dataset to obtain the declouded second time series dataset; based on the maximum synthesis method, performing low-quality pixel removal on the declouded second time series dataset to obtain the low-quality pixel removal second time series dataset.

[0045] That is, a machine learning model is used to identify and extract pixels with cloud pollution in each image data of the second time series dataset, and the maximum NDVI value of each pixel is selected from the image data of the second time series dataset to generate synthetic data with a 16-day interval to reduce the impact of cloud cover.

[0046] Furthermore, for the above-mentioned S101, the purpose of performing multi-temporal segmentation on the target area is: by performing multi-temporal segmentation on the target area, various homogeneous areas in the target area with uniform changes in the normalized vegetation index are obtained, and then in the subsequent process of data filling of the image data of the second time series data set, the homogeneous object is used as the basic unit to improve the structural correlation and filling efficiency between the filled data and the target area during the data filling process.

[0047] Specifically, the above S101 includes: using a simple non-iterative clustering algorithm, combining the spatial distribution of the image data of the second time series data set in the target area and the temporal distribution between different image data, performing multi-phase segmentation on the target area, and determining the various homogeneous areas of the target area.

[0048] Please refer to Figure 2 , Figure 2 A schematic diagram of a homogeneous region of a target region provided in an embodiment of the present application.

[0049] like Figure 2 As shown, Figure 2 The target area is composed of a first homogeneous area 201, a second homogeneous area 202, a third homogeneous area 203, and a fourth homogeneous area 204. These homogeneous areas together constitute the target area, and each pixel in the homogeneous area corresponds to an NDVI value. The NDVI values ​​of each pixel in each homogeneous area are similar in time and space, that is, the NDVI values ​​of each pixel in the same homogeneous area are similar in an image data of the second time series data set, and the differences in images of different time series are uniform.

[0050] In actual application, the multi-temporal segmentation of the target area using a simple non-iterative clustering algorithm can be implemented based on the Google Earth Engine platform. Specifically, during the platform application, the compactness of the simple non-iterative clustering algorithm can be set to 0, the seed size to 15, the neighborhood range to 40, and the connectivity to 8.

[0051] S102 , based on the image data of each homogeneous area in the first time series data set of the target area and the second time series data set, numerically correct the first time series data set corresponding to each homogeneous area to obtain a numerically corrected first time series data set.

[0052] Similar to the second time series dataset mentioned above, the image data of the first time series dataset also refers to the pre-processed Normalized Difference Vegetation Index (NDVI) covering the target area.

[0053] In the embodiment of the present application, the first time series data set is a basic condition for filling the second time series data set.

[0054] In actual application, the first time series data set can be obtained by collecting the Moderate Resolution Imaging Spectroradiometer (MODIS) on Terra and Aqua satellites, with a spatial resolution of 250 meters and a temporal resolution of 16 days. MODIS usually includes MOD13Q1 and MYD13Q1. In actual application, in order to further improve the temporal resolution of the NDVI data collected by MODIS and to provide higher reconstruction accuracy to fill the NDVI data collected by MODIS, the NDVI data collected by MOD13Q1 and MYD13Q1 can be synthesized by selecting the best value from all 16 days of NDVI data based on the coverage, clouds and aerosols of the image data collected by MOD13Q1 and MYD13Q1 to generate NDVI data with higher temporal resolution (8 days).

[0055] Considering that the image data collected by MODIS and Sentinel-2 satellites may have different time intervals, the image data collected by MODIS can also be declouded and repaired to improve the quality of the first time series dataset.

[0056] In order to improve the data quality of the first time series data set, the method also includes: using a declouding algorithm to decloud the various image data in the first time series data set to obtain a first time series data set after declouding; using time harmonic analysis to remove noise from the first time series data set after declouding, and filling in missing time series values ​​in the first time series data set to obtain a first time series data set after noise removal and missing time series value filling; using bicubic convolution interpolation to fill in spatial missing values ​​in the first time series data set after noise removal and missing time series value filling to obtain a first time series data set after missing time series value filling.

[0057] Furthermore, the above S102 includes the following S1 and S2.

[0058] S1 , based on the median of the difference between each image data of the first time series data set in the homogeneous area, updating the image data in the first time series data set to obtain an updated first time series data set.

[0059] The purpose of updating the image data in the first time series data set is to eliminate the difference in NDVI changes between the image data at the same time in the first time series data set and the second time series data set.

[0060] For easier understanding, please refer to Figure 3 , Figure 3 The data curve provided for the embodiment of this application Figure 1 .

[0061] like Figure 3 As shown, Figure 3 It includes: the updated MODIS NDVI data curve (i.e., the data curve corresponding to the updated first time series dataset), and the discrete Sentinel-2 NDVI data (i.e., the data points of the second time series dataset).

[0062] The updated MODIS NDVI data curve specifically refers to the change curve of the MODIS NDVI data of the pixel corresponding to a certain position in the MODIS image data of a homogeneous area within a preset time range, and the discrete Sentinel-2 NDVI data refers to the NDVI data of the pixel corresponding to the position in the Sentinel-2 image data of the homogeneous area.

[0063] based on Figure 3 It can be seen that the changing trend of the updated MODIS NDVI data curve is roughly the same as that of the discrete Sentinel-2 NDVI data.

[0064] In the prior art, a similar pixel search method (GF-SG) is usually used to search for similar pixels near the target pixel to eliminate the difference in NDVI changes between the first time series dataset and the second time series dataset. The principle is shown in the following formula (1): (1); in, Represents the reference timing data of the target pixel; represents the position of the target pixel in the image data of the first time series dataset and the second time series dataset, wherein the position of the target pixel in the influence data of the first time series dataset and the second time series dataset is the same; j represents the jth similar pixel of the target pixel; n represents the total number of similar pixels of the target pixel; represents the data matrix composed of the NDVI data corresponding to the j-th similar pixel in the image data of the first time series dataset; represents the position of the jth similar pixel in the target area; represents the correlation coefficient between the jth similar pixel and the target pixel.

[0065] That is, the NDVI data of all similar pixels are added according to the weights to generate the reference time series data of the target pixel, and the reference time series data of each target pixel is used as the time series data set after the change difference is eliminated.

[0066] However, this method usually requires the use of a moving window to search for similar pixels to the target pixel, which is usually accompanied by a lot of calculations. In addition, this pixel-level data update method ignores the inherent shape information of ground objects and the regional similarity and temporal correlation characteristics of the normalized vegetation index, which easily causes intra-class salt and pepper noise.

[0067] In order to solve this problem, the normalized vegetation index filling method provided in the embodiment of the present application updates the first time series data set based on the homogeneous areas of the target area obtained in the above S101, taking the homogeneous areas as the objects to eliminate the NDVI change differences between the various image data of the first time series data set.

[0068] Specifically, the above S1 includes the following S11 to S14.

[0069] S11 , for any of the homogeneous regions, using the image data with the first time sequence in the first time series data set corresponding to the homogeneous region as reference data.

[0070] S12, determining first update data according to the median of the difference between the image data at the second position in the time sequence in the first time series data set and the reference data; and updating the image data at the second position in the time sequence in the first time series data set according to the first update data and the reference data.

[0071] S13, determining the second updated data according to the median of the difference between the image data ranked third in time sequence in the first time series data set and the image data ranked second in time sequence; updating the image data ranked third in time series data set according to the first updated data, the second updated data and the reference data.

[0072] The purpose of using the median between the differences is to eliminate the influence of low-quality pixels in the image data on the normalized vegetation index of the homogeneous area.

[0073] S14, and so on, until each image data in the first time series data set is traversed to obtain an updated first time series data set.

[0074] Specifically, the above process of updating each image data in the first time series data set can be expressed by the following formula (2) and formula (3): (2); (3); in, represents the nth image data in the first time series data set after update, where n is an integer greater than or equal to 2; represents the image data with the first time sequence in the first time series data set; represents the image data ranked at the i-th position in the first time series data set; represents the median of the difference between the normalized vegetation index of each image data ranked at the i-th position and each image data ranked at the i-1th position in the first time series data set in the homogeneous area; Indicates the updated image data of the first time series dataset at coordinates The normalized vegetation index sequence corresponding to the pixels.

[0075] S2: Perform numerical correction on the updated first time series dataset according to the second time series dataset to obtain a numerically corrected first time series dataset.

[0076] The purpose of performing numerical correction on the updated first time series data set is to eliminate the numerical difference between the first time series data set and the second time series data set.

[0077] Please refer to Figure 4 , Figure 4 The data curve provided for the embodiment of this application Figure 2 .

[0078] Figure 4 The graph includes the updated MODIS NDVI data curve (i.e., the data curve corresponding to the updated first time series dataset), the discrete Sentinel-2 NDVI data (i.e., the data points corresponding to the second time series dataset), and the numerically corrected MODIS NDVI data curve (i.e., the data curve corresponding to the numerically corrected first time series dataset).

[0079] according to Figure 4 It can be seen that compared with the numerically corrected MODIS NDVI data curve, the updated MODIS NDVI data curve eliminates the amplitude difference between the numerically corrected MODIS NDVI data and the discrete Sentinel-2 NDVI data.

[0080] Specifically, the above S2 includes: taking each image data in the second time series data set as a target, using a linear transfer function to perform numerical correction on each image data in the first time series data set to obtain a corrected first time series data set.

[0081] The numerical correction of each image data in the first time series data set using a linear transfer function can be expressed by the following formula (4): (4); in, express Each image data is at coordinates The normalized vegetation index sequence corresponding to the pixels; and Indicates that the first time series dataset after update is at coordinate Correction coefficient of the normalized vegetation index of the pixel; and By minimizing the corrected first time series data set and The difference between them is obtained; Indicates the updated image data of the first time series dataset at coordinates The normalized vegetation index sequence corresponding to the pixels.

[0082] S103 , based on the corrected first time series data set, performing missing value filling on the missing image data in the second time series data set to obtain a second time series data set after missing value filling.

[0083] The above S103 refers to using the corrected image data of the first time series dataset as the missing image data in the second time series dataset, thereby completing the filling of the missing values ​​of the second time series dataset.

[0084] In practical applications, considering that the second time series dataset may have low quality values, the weighted Savitzky-Golay (SG) filter can be used to denoise the padded second time series dataset, so as to remove cloud contamination and sensor errors while retaining the change trend of NDVI in each image data in the second time series dataset.

[0085] Please refer to Figure 5 , Figure 5 The data curve provided for the embodiment of this application Figure 3 .

[0086] like Figure 5 As shown in Figure 5, the Sentinel-2 NDVI data curve after missing value filling and the Sentinel-2 NDVI data curve after filtering are included.

[0087] according to Figure 5 The filtered Sentinel-2 NDVI data curve shown is smoother than the Sentinel-2 NDVI data curve after missing value filling.

[0088] In the weighted Savitzky-Golay (SG) filtering method, the weight is modified by two adjustment factors during the weighting process. Specifically, for each image data in the original second time series data set, its weight is set to 1. For the padded image data, its weight can be expressed by the following formula (5): (5); in, represents the weight of the i-th padded image data; It represents the NDVI standard deviation between adjacent pixels in the window centered on the target pixel in the i-th padded image data; express The maximum value in .

[0089] In actual application, the half-width of the window can be set to 4, and the degree of the smoothing polynomial used in the weighted Savitzky-Golay (SG) filter is set to 6.

[0090] Furthermore, in order to evaluate the filling method of the normalized vegetation index provided in the embodiment of the present application, the root mean square error, mean deviation and edge information were used to quantitatively analyze the accuracy of the first time series data set after filling.

[0091] Specifically, the root mean square error, mean deviation, and Edge index can be calculated using the following formulas (6) to (8): (6); (7); (8); in, represents the root mean square error; represents the NVDI value of the i-th pixel in the image data of the second time series dataset after missing values ​​are filled; represents the NVDI value of the i-th pixel in the image data of the reference time series dataset; N represents the total number of pixels in the image data; represents the mean deviation; Represents edge information; Indicates the NDVI value corresponding to the pixel in the x-th row and y-th column in the image data.

[0092] In order to quantitatively analyze the filling method of the normalized vegetation index provided in the embodiment of the present application, the study selected the NDVI image collected by Sentinel-2 in the Erhai Lake Basin on January 17, 2019 as the image data, and used the NDVI image of the area on January 14, 2019 as a reference for quantitative analysis of the accuracy, and obtained RMSE, AD, and Edge as 0.0615, 0.0390, and -0.1297, respectively. These data indicate that the filling method of the normalized vegetation index has high accuracy in filling the missing image data and can meet the production needs of NVDI products.

[0093] In addition, during the process of filling the normalized vegetation index values ​​on the GEE platform, the above S101 to S103 took a total of about 15 minutes, indicating that this method has high feasibility and efficiency in NDVI reconstruction work at a large regional scale.

[0094] In summary, the method for filling the normalized vegetation index provided in the embodiment of the present application performs multi-phase segmentation on the second time series data set of the target area to obtain the various homogeneous areas of the target area, and uses the homogeneous unit as the correction unit, and numerically corrects the first time series data set whose spatial resolution of the target area is smaller than that of the second time series data set in combination with the second time series data set, and fills the missing values ​​of the missing image data in the second time series data set based on the numerically corrected first time series data set. This method divides the target area by performing multi-phase segmentation on the target area in combination with the second time series data set, taking into account the spatial distribution and temporal distribution of the normalized vegetation index, which helps to improve the data quality of the corrected first time series data set in combination with the spatial distribution and temporal distribution of the normalized vegetation index in the process of numerically correcting the first time series data set, and improve the data quality of the second time series data set after the missing values ​​are filled.

[0095] The present application also provides a device for filling in the normalized vegetation index. Figure 6 , Figure 6 This is a structural diagram of the normalized vegetation index filling device provided in an embodiment of the present application.

[0096] like Figure 6 As shown, the filling device of the normalized vegetation index includes: The time phase segmentation unit 601 is configured to perform multi-time phase segmentation on the target region according to the second time series data set of the target region, and determine each homogeneous region of the target region.

[0097] The numerical correction unit 602 is used to perform numerical correction on the first time series data set corresponding to each homogeneous area in the first time series data set of the target area and the second time series data set, to obtain a numerically corrected first time series data set; wherein each pixel in the image data of the first time series data set and the second time series data set corresponds to a normalized vegetation index; and the spatial resolution of each image data of the first time series data set is smaller than the spatial resolution of each image data of the second time series data set.

[0098] The value filling unit 603 is used to fill missing values ​​in the missing image data in the second time series data set based on the corrected first time series data set to obtain a second time series data set after missing value filling.

[0099] In an optional embodiment of the present application, the target area is segmented into multiple temporal phases based on the second time series data set of the target area to determine the various homogeneous areas of the target area, including: using a simple non-iterative clustering algorithm, combining the spatial distribution of the image data of the second time series data set in the target area and the temporal distribution between different image data, to perform multi-temporal segmentation on the target area to determine the various homogeneous areas of the target area.

[0100] In an optional embodiment of the present application, based on the image data of each homogeneous area in the first time series data set of the target area and the second time series data set, the first time series data set corresponding to each homogeneous area is numerically corrected to obtain a numerically corrected first time series data set, including: updating the image data in the first time series data set based on the median of the difference between each image data of the first time series data set in the homogeneous area to obtain an updated first time series data set; and numerically correcting the updated first time series data set based on the second time series data set to obtain a numerically corrected first time series data set.

[0101] In an optional embodiment of the present application, the image data in the first time series data set is updated based on the median of the difference between each image data in the first time series data set in the homogeneous area to obtain an updated first time series data set, including: for any of the homogeneous areas, taking the image data in the first time series data set corresponding to the homogeneous area as the reference data; determining the first update data based on the median of the difference between the image data in the second time series data set and the reference data; updating the image data in the second time series data set based on the first update data and the reference data; determining the second update data based on the median of the difference between the image data in the third time series data set and the image data ranked second in the first time series data set; updating the image data ranked third in the first time series data set based on the first update data, the second update data and the reference data; and so on, until each image data in the first time series data set is traversed to obtain an updated first time series data set.

[0102] In an optional implementation manner of the present application, the image data in the first time series data set is updated using the following formula to obtain an updated first time series data set: ; ; in, represents the nth image data in the first time series data set after update, where n is an integer greater than or equal to 2; represents the image data with the first time sequence in the first time series data set; represents the image data ranked at the i-th position in the first time series data set; represents the median of the difference between the normalized vegetation index of each image data ranked at the i-th position and each image data ranked at the i-1th position in the first time series data set in the homogeneous area; Indicates the updated image data of the first time series dataset at coordinates The normalized vegetation index sequence corresponding to the pixels.

[0103] In an optional embodiment of the present application, the updated first time series data set is numerically corrected based on the second time series data set to obtain the numerically corrected first time series data set, including: taking each image data in the second time series data set as the target, using a linear transfer function to numerically correct each image data in the first time series data set to obtain the corrected first time series data set.

[0104] In an optional implementation of the present application, the updated first time series data is numerically corrected using the following formula to obtain a numerically corrected first time series data set: ; in, Indicates the coordinates of each image data in the second time series data set The normalized vegetation index sequence corresponding to the pixels; and Indicates that the first time series dataset after update is at coordinate Correction coefficient of the normalized vegetation index of the pixel; and By minimizing the corrected first time series data set and The difference between them is obtained; Indicates the updated image data of the first time series dataset at coordinates The normalized vegetation index sequence corresponding to the pixels.

[0105] Compared with the prior art, the beneficial effects of the normalized vegetation index filling device provided by the present invention are the same as the beneficial effects of the normalized vegetation index filling method described in the above technical solution, and are not described in detail here.

[0106] The above method embodiment provided in this embodiment and the system embodiment of this application belong to the same application concept. For technical details not fully described in this embodiment, please refer to the specific processing content of the normalized vegetation index filling method provided in the above embodiment of this application, which will not be repeated here.

[0107] The present application also provides an electronic device, such as Figure 7 As shown, Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0108] like Figure 7 As shown, the electronic device includes: Processor 210.

[0109] The memory 200 is used to store instructions executable by the processor 210.

[0110] The processor 210 is configured to execute the normalized vegetation index filling method disclosed in any of the above embodiments by running instructions in the memory 200 .

[0111] The processor 210 , the memory 200 , the communication interface 220 , the input device 230 , and the output device 240 are connected to each other via a bus.

[0112] A bus may include a pathway that transfers information between components of a computer system.

[0113] Processor 210 can be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, or the like. It can also be an application-specific integrated circuit (ASIC), or one or more integrated circuits used to control the execution of the program of the present invention. It can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic device, or discrete hardware components.

[0114] The processor 210 may include a main processor, and may also include a baseband chip, a modem, and the like.

[0115] Memory 200 stores programs that implement the technical solutions of the present invention and may also store an operating system and other key services. Specifically, the programs may include program code, which includes computer operating instructions. More specifically, memory 200 may include read-only memory (ROM), other types of static storage devices capable of storing static information and instructions, random access memory (RAM), other types of dynamic storage devices capable of storing information and instructions, disk storage, flash memory, and the like.

[0116] The input device 230 may include a device for receiving data and information input by a user, such as a keyboard, a mouse, a camera, a scanner, a touch screen, etc.

[0117] Output device 240 may include devices that allow information to be output to a user, such as a display screen, printer, speakers, etc.

[0118] The communication interface 220 may include any device such as a transceiver to communicate with other devices or communication networks, such as Ethernet, a radio access network (RAN), a wireless local area network (WLAN), etc.

[0119] The processor 210 executes the program stored in the memory 200 and calls other devices, and can be used to implement each step of any normalized vegetation index filling method provided in the above embodiments of the present application.

[0120] In addition to the above methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps in the normalized vegetation index filling method of various embodiments of the present application.

[0121] The computer program product may be written in any combination of one or more programming languages ​​to implement the program code for performing the operations of the embodiments of the present application, including object-oriented programming languages ​​such as Java, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0122] In addition, the embodiment of the present application may also be a storage medium on which a computer program is stored, and the computer program is used by a processor to execute the steps in the normalized vegetation index filling method of various embodiments of the present application.

[0123] For the sake of simplicity, the aforementioned method embodiments are described as a series of action combinations. However, those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, 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 this specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0124] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similarities between the various embodiments can be referred to in conjunction with each other. For device embodiments, since they are generally similar to method embodiments, their description is relatively simple, and for relevant details, reference can be made to the description of the method embodiments.

[0125] The steps in the methods of each embodiment of the present application can be adjusted in sequence, merged, and deleted according to actual needs, and the technical features recorded in each embodiment can be replaced or combined.

[0126] The modules and sub-modules in the devices and terminals in the various embodiments of the present application can be merged, divided, and deleted according to actual needs.

[0127] In the several embodiments provided in this application, it should be understood that the disclosed terminals, devices, and methods can be implemented in other ways. For example, the terminal embodiments described above are merely illustrative. For example, the division of modules or submodules is merely a logical function division. In actual implementation, there may be other division methods, such as multiple submodules or modules can be combined or integrated into another module, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or module, which can be electrical, mechanical or other forms.

[0128] The modules or submodules described as separate components may or may not be physically separate, and the components of the modules or submodules may or may not be physical modules or submodules, that is, they may be located in one place or distributed across multiple network modules or submodules. Some or all of the modules or submodules may be selected to achieve the purpose of this embodiment according to actual needs.

[0129] In addition, each functional module or submodule in each embodiment of the present application may be integrated into a processing module, or each module or submodule may exist physically separately, or two or more modules or submodules may be integrated into a single module. The above-mentioned integrated modules or submodules may be implemented in the form of hardware or software functional modules or submodules.

[0130] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the components and steps of each example according to their functions. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0131] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, software executed by a processor, or a combination of the two. The software may be stored in random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0132] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or device comprising the element.

[0133] The above description of the disclosed embodiments will enable those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is to be construed in the widest manner consistent with the principles and novel features disclosed herein.

Claims

1. A method for filling the normalized vegetation index, characterized in that: include: performing multi-temporal segmentation on the target region according to the second time series data set of the target region to determine homogeneous regions of the target region; performing numerical correction on the first time series data set corresponding to each homogeneous area in the first time series data set of the target area and the second time series data set to obtain a numerically corrected first time series data set; wherein each pixel in the image data of the first time series data set and the second time series data set corresponds to a normalized vegetation index; and the spatial resolution of each image data of the first time series data set is smaller than the spatial resolution of each image data of the second time series data set; Based on the corrected first time series data set, missing value filling is performed on the missing image data in the second time series data set to obtain a second time series data set after missing value filling.

2. The method for filling the normalized vegetation index according to claim 1, characterized in that: The step of performing multi-temporal segmentation on the target region based on the second time series data set of the target region to determine homogeneous regions of the target region includes: A simple non-iterative clustering algorithm is used to combine the spatial distribution of the image data of the second time series data set in the target area and the temporal distribution between different image data to perform multi-temporal segmentation on the target area and determine the homogeneous areas of the target area.

3. The method for filling the normalized vegetation index according to claim 1, characterized in that: The method of performing numerical correction on the first time series data sets corresponding to the homogeneous regions in the first time series data set of the target region and the second time series data set to obtain the numerically corrected first time series data sets includes: updating the image data in the first time series dataset based on the median of the difference between each image data in the first time series dataset in the homogeneous area to obtain an updated first time series dataset; According to the second time series data set, the updated first time series data set is numerically corrected to obtain a numerically corrected first time series data set.

4. The method for filling the normalized vegetation index according to claim 3, characterized in that: The method includes updating the image data in the first time series dataset based on the median of the difference between each image data in the homogeneous area to obtain an updated first time series dataset, including: For any of the homogeneous regions, the image data with the first time sequence in the first time series data set corresponding to the homogeneous region is used as the reference data; determining first update data according to a median of a difference between the image data at the second position in the time sequence in the first time series data set and the reference data; and updating the image data at the second position in the time sequence in the first time series data set according to the first update data and the reference data; Determining second update data based on a median of a difference between the image data ranked third in time sequence and the image data ranked second in time sequence in the first time series data set; and updating the image data ranked third in time sequence in the first time series data set based on the first update data, the second update data, and the reference data; The same process is repeated until each image data in the first time series data set is traversed to obtain an updated first time series data set.

5. The method for filling the normalized vegetation index according to claim 3 or 4, characterized in that: The image data in the first time series dataset is updated using the following formula to obtain an updated first time series dataset: ； ； in, represents the nth image data in the first time series data set after update, where n is an integer greater than or equal to 2; represents the image data with the first time sequence in the first time series data set; represents the image data ranked at the i-th position in the first time series data set; represents the median of the difference between the normalized vegetation index of each image data ranked at the i-th position and each image data ranked at the i-1th position in the first time series data set in the homogeneous area; Indicates the updated image data of the first time series dataset at coordinates The normalized vegetation index sequence corresponding to the pixels.

6. The method for filling the normalized vegetation index according to claim 3, characterized in that: The step of performing numerical correction on the updated first time series dataset based on the second time series dataset to obtain the numerically corrected first time series dataset includes: Taking each image data in the second time series data set as a target, a linear transfer function is used to perform numerical correction on each image data in the first time series data set to obtain a corrected first time series data set.

7. The method for filling the normalized vegetation index according to claim 3 or 6, characterized in that: The updated first time series data is numerically corrected using the following formula to obtain the numerically corrected first time series data set: ； in, Indicates the coordinates of each image data in the second time series data set The normalized vegetation index sequence corresponding to the pixels; and Indicates that the first time series dataset after update is at coordinate Correction coefficient of the normalized vegetation index of the pixel; and By minimizing the corrected first time series data set and The difference between them is obtained; Indicates the updated image data of the first time series dataset at coordinates The normalized vegetation index sequence corresponding to the pixels.

8. A device for filling the normalized vegetation index, characterized in that: include: a time phase segmentation unit, configured to perform multi-time phase segmentation on the target region according to the second time series data set of the target region, and determine each homogeneous region of the target region; a numerical correction unit, configured to perform numerical correction on the image data of each homogeneous area in the first time series data set of the target area to obtain a numerically corrected first time series data set; wherein each pixel in the image data of the first time series data set and the second time series data set corresponds to a normalized vegetation index; and the spatial resolution of each image data of the first time series data set is greater than the spatial resolution of each image data of the second time series data set; The value filling unit is used to fill missing values ​​of the missing image data in the second time series data set based on the corrected first time series data set to obtain the second time series data set after the missing values ​​are filled.

9. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the normalized vegetation index filling method according to any one of claims 1 to 7 by running instructions in a memory.

10. A computer storage medium, characterized in that The computer storage medium stores instructions, and when the instructions are executed, the method for filling the normalized vegetation index according to any one of claims 1 to 7 is executed.

Images