A method for remote sensing extraction of arable land boundaries

Abstract

The present application relates to the technical field of remote sensing, and particularly relates to a remote sensing extraction method for cultivated land boundary, comprising the following steps: selecting high-resolution remote sensing images in a natural year of a research area, and making in-year time-series NDVI image data; performing edge detection, spatial superposition, cultivated land range extraction and other land class mask processing on the in-year time-series NDVI image data, so as to obtain a potential cultivated land edge cumulative frequency graph; classifying cultivated land edges in the potential cultivated land edge cumulative frequency graph into permanent edges, temporary edges and non-edges through an automatic threshold segmentation algorithm, retaining the permanent edges, and obtaining a cultivated land boundary graph; verifying the extraction accuracy of the cultivated land boundary by calculating ECR values, using a confusion matrix and Spearman correlation analysis, and comparing with a Geo-Wiki Field Size data set. The present application is simple to operate, has high extraction efficiency and accuracy, and is conducive to cultivated land boundary detection and control.

Description

Technical Field

[0001] The invention relates to the fields of land use change, ground feature extraction and remote sensing technology, and in particular to a remote sensing extraction method for cultivated land boundaries. Background Art

[0002] Arable land is essential for human survival. The quantity and quality of arable land determine a country's population carrying capacity and sustainable development capabilities. It bears the heavy responsibility of providing food security for humanity and is a crucial guarantee for national ecological security. Using remote sensing technology to accurately obtain arable land boundary information, obtain dynamic arable land monitoring data, and form comprehensive land assessments are crucial for guiding agricultural decision-making and implementing comprehensive land management. Accurate and timely arable land boundary information is crucial for agricultural development, resource management, and other related fields.

[0003] Cultivated land boundaries are crucial agricultural data. Traditionally, field surveys are used to obtain them. However, these methods produce statistical results with very coarse temporal and spatial resolution. Due to high costs, systematic surveys are typically conducted only every few years, and data released at the smallest administrative level cannot accurately describe spatial variations. For high-resolution imagery, some researchers have employed visual interpretation to interpret remote sensing images and mark cultivated land boundaries within sample areas. However, due to the inevitable subjective interference and high labor costs associated with manual interpretation, this method cannot be used as a routine monitoring tool. With the continuous advancement of global remote sensing satellite observation technology and computers, remote sensing methods have become an effective and reliable means of obtaining spatially explicit and objective data, overcoming the shortcomings of manual interpretation. Research on automated mapping of cultivated land boundaries using remote sensing imagery can be broadly categorized into edge-based, region-based, and hybrid algorithms. While these algorithms have been successfully applied in large-scale farmland areas such as the United States and Europe, they have struggled to achieve satisfactory results in small-scale agricultural areas. In small-scale agricultural areas, cultivated land boundaries are smaller and more fragmented, with thinner boundaries between fields, typically less than 10 meters, which is smaller than the spatial resolution of the image. Therefore, extracting cultivated land boundaries in small-scale agricultural areas is extremely challenging. Summary of the Invention

[0004] In order to solve the problems of farmland boundary extraction and land utilization in small-scale agricultural areas, the present invention proposes a remote sensing extraction method for farmland boundaries with small boundary area and high degree of fragmentation.

[0005] In order to achieve the above object, the technical solutions specifically adopted by the present invention are as follows:

[0006] A remote sensing extraction method for cultivated land boundaries comprises the following steps:

[0007] S1. Select high-resolution remote sensing images of the study area within a natural year and produce time-series NDVI image data within the year;

[0008] S2. Processing the intra-year time series NDVI data images through edge detection, spatial overlay, cultivated land range extraction, and other land type masking to obtain a potential cultivated land edge cumulative frequency map;

[0009] S3, classifying the cultivated land edges in the potential cultivated land edge cumulative frequency map into permanent edges, temporary edges, and non-edges by an automatic threshold segmentation algorithm, retaining the permanent edges, and obtaining a cultivated land boundary map;

[0010] S4. The accuracy of cultivated land boundary extraction was verified by calculating the ECR value, using confusion matrix and Spearman correlation analysis, and comparing with the Geo-Wiki FieldSize dataset.

[0011] Furthermore, in step S1, Sentinel-2 remote sensing images within a natural year are selected, and the NDVI value of each remote sensing image is calculated using red light band and near infrared band data, specifically including the following steps:

[0012] S11. Select Sentinel-2 remote sensing images of the study area within one natural year;

[0013] S12. Calculate the percentage of clean pixels in the Sentinel-2 remote sensing image based on the QA bands, discard images with a clean pixel percentage less than 99%, and retain images with a clean pixel percentage greater than 99%;

[0014] S13. Calculate the NDVI value of each remote sensing image obtained in step S12 using the 10m resolution Red band and NIR band in the Sentinel-2 remote sensing image. The formula is as follows:

[0015]

[0016] Where NDVI is the Normalized Difference Vegetation Index, an important parameter reflecting crop growth and nutritional information; NIR is the reflectance of the near-infrared band of the remote sensing image; and Red is the reflectance of the red light band of the remote sensing image.

[0017] Furthermore, in step S2, based on the 10m resolution annual time-series NDVI data image obtained in step S1, an edge detection algorithm is used to identify the edges in each image; a spatial overlay method is applied to obtain the cumulative number of each edge; land use data is used to extract the scope of cultivated land in the study area, and other land types such as built-up areas, water bodies, and forests are masked to obtain a potential cultivated land edge cumulative number map.

[0018] Furthermore, the step S2 specifically includes the following steps:

[0019] S21, using the Canny edge detection algorithm, performing convolution calculation on the NDVI value of each remote sensing image obtained in step S1, extracting the area (edge) where the grayscale changes suddenly, and forming a binary image;

[0020] S22, performing equal-weighted summing and superposition processing on each binary image obtained in step S21 to produce a potential edge frequency map;

[0021] S23. Using the cultivated land in the WorldCover product (2021) as the target land type, perform mask processing on the potential edge frequency map in step S22 to obtain a potential cultivated land edge cumulative frequency map.

[0022] Furthermore, in step S21, the threshold of the Canny edge detection algorithm is set to 100, and Sigma is set to 1.5.

[0023] Furthermore, the step S3 specifically includes the following steps:

[0024] S31, using the OTSU automatic threshold segmentation algorithm once, dividing the edges in the potential cultivated land edge cumulative frequency map obtained in step S2 into true edges and non-edges;

[0025] S32, performing convolution calculation on the true edge obtained in step 31 using the OTSU automatic threshold segmentation algorithm to divide the true edge into permanent edges and temporary edges;

[0026] S33. By eliminating non-edges and temporary edges and retaining permanent edges, a stable farmland boundary map is obtained.

[0027] Furthermore, the step S4 includes the following steps:

[0028] S41, using spatial analysis tools to calculate the permanent edge ratio per unit area of ​​cultivated land based on the stable cultivated land boundary map obtained in step S3;

[0029]

[0030] Where ECR is the cultivated land margin ratio. Ideally, the lower the ECR value, the larger the farmland area, and the smaller the permanent margin ratio.

[0031] S42. Based on the Geo-Wiki Field Size dataset, within a 1600m radius grid around the sampling point, the classification threshold is determined by the correlation coefficient method and expert experience, and the farmland is divided into four size classes: L, M, S, and XS according to the ECR value of the cultivated land;

[0032] S43. The consistency between the cultivated land size predicted based on the ECR value and the cultivated land size in the Geo-Wiki Field Size dataset was analyzed through the confusion matrix, and Spearman correlation analysis was performed on the two variables.

[0033]

[0034] Where ρ is the Spearman correlation coefficient, and its value range is [-1, 1]; ρ>0 indicates a positive correlation between the two variables, ρ<0 indicates a negative correlation, and ρ=0 indicates no linear correlation between the two variables; the absolute value of the coefficient indicates the strength of the correlation, and the closer the value is to 1, the stronger the correlation.

[0035] Furthermore, in step S42, the classification thresholds of L, M, S and XS are 0.074, 0.085 and 0.099 respectively.

[0036] The present invention has the following characteristics and beneficial effects:

[0037] The present invention utilizes long-term remote sensing image data, combined with land use data and cultivated land data, and adopts edge detection, automatic threshold segmentation and other algorithms to construct cultivated land boundary extraction rules, realize the extraction of cultivated land boundaries, and facilitate the monitoring of cultivated land fragmentation.

[0038] The invention is simple to operate, has high extraction efficiency and accuracy, greatly reduces the workload of manual vectorization, and realizes remote sensing extraction of cultivated land boundary information in the absence of high-temporal and spatial resolution image information and limited human subjective conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Other features, objects and advantages of the present invention will become more apparent upon reading the detailed description of non-limiting embodiments with reference to the following drawings:

[0040] Figure 1 This is a process for producing a cumulative frequency map of potential farmland edges in a certain area in an embodiment of the present invention;

[0041] Figure 2 All edges and permanent edges of cultivated land in a certain area in the embodiment of the present invention;

[0042] Figure 3 The probability density district and confusion matrix results of the ECR value of a certain region in an embodiment of the present invention are shown. DETAILED DESCRIPTION

[0043] The present invention is described in detail below in conjunction with specific embodiments. The following examples will help those skilled in the art to further understand the present invention, but are not intended to limit the present invention in any form. It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other.

[0044] To address the current challenges in extracting cultivated land boundaries in small-scale agricultural areas with small boundaries and high fragmentation, this paper proposes a remote sensing method for extracting cultivated land boundaries. This method is based on long-term remote sensing image data, combined with land use data and cultivated land data. It utilizes edge detection, automatic threshold segmentation, and other algorithms to construct cultivated land boundary extraction rules, which is beneficial for the extraction and monitoring of cultivated land boundaries. Specifically, the method includes the following steps:

[0045] S1. Produce time series NDVI image data within the year;

[0046] High-resolution remote sensing images of the study area within one natural year were selected, and the NDVI value of each remote sensing image was calculated using red light band and near-infrared band data; specifically:

[0047] S11. Select Sentinel-2 remote sensing images within one natural year within the study area;

[0048] S12. Calculate the percentage of clean pixels in the Sentinel-2 remote sensing image based on the QA bands, discard images with a clean pixel percentage less than 99%, and retain images with a clean pixel percentage greater than 99%;

[0049] S13. Calculate the NDVI value of each remote sensing image processed in step S12 using the 10m resolution Red band and NIR band in the Sentinel-2 remote sensing image. The formula is as follows:

[0050]

[0051] Where NDVI is the Normalized Difference Vegetation Index, an important parameter reflecting crop growth and nutritional information; NIR is the reflectance of the near-infrared band of the remote sensing image; and Red is the reflectance of the red light band of the remote sensing image.

[0052] S2. Create a cumulative frequency map of potential cultivated land edges;

[0053] Based on the 10m resolution annual time-series NDVI data images obtained in step S1, an edge detection algorithm is used to identify the edges in each image; a spatial overlay method is used to obtain the cumulative number of each edge; land use data is used to extract the scope of cultivated land in the study area, and other land types such as built-up areas, water bodies, and forests are masked to obtain a potential cultivated land edge cumulative number map: Specifically:

[0054] S21, using the Canny edge detection algorithm, performing convolution calculation on each NDVI data obtained in step S1, extracting the area (edge) where the grayscale changes suddenly, and forming a binary image;

[0055] S22, performing equal-weighted summing and superposition processing on each binary image obtained in step S21 to produce a potential edge frequency map;

[0056] S23, using the cultivated land in the WorldCover product (2021) as the target land type, performing mask processing on the potential edge frequency map in step S22 to obtain a potential cultivated land edge cumulative frequency map;

[0057] S3. Prepare a stable farmland boundary map;

[0058] Based on the potential cultivated land edge cumulative frequency map obtained in step S2, the cultivated land edges are classified by the automatic threshold segmentation algorithm to obtain permanent edges, temporary edges and non-edges. The permanent edges are retained to produce a stable cultivated land boundary map. Specifically:

[0059] S31, using the OTSU automatic threshold segmentation algorithm once, dividing the edges in the potential cultivated land edge cumulative frequency map obtained in step S2 into true edges and non-edges;

[0060] S32, for the true edge obtained in step S31, the OTSU automatic threshold segmentation algorithm is again used to perform convolution calculation to divide the true edge into permanent edges and temporary edges;

[0061] S33. By eliminating non-edges and temporary edges and retaining permanent edges, a stable farmland boundary map is obtained.

[0062] S4, accuracy verification;

[0063] For the stable cultivated land boundary map obtained in step S3, the ratio of the edge area per unit cultivated land area is calculated and compared with the Geo-Wiki Field Size dataset using methods such as confusion matrix and Spearman correlation analysis to verify the accuracy of the method:

[0064] S41, using spatial analysis tools to calculate the permanent edge ratio per unit area of ​​cultivated land on the stable cultivated land boundary map in step S3;

[0065]

[0066] Where ECR is the cultivated land margin ratio. Ideally, the lower the ECR value, the larger the farmland area, and the smaller the permanent margin ratio.

[0067] S42. Based on the 1600m radius grid around the sampling point of the Geo-Wiki Field Size dataset, farmland is divided into four size classes according to the ECR value of cultivated land using the correlation coefficient method and expert experience. The classification criteria are shown in the following table:

[0068]

[0069] S43. The consistency between the cultivated land size predicted based on the ECR value and the cultivated land size in the Geo-Wiki Field Size dataset was analyzed through the confusion matrix, and Spearman correlation analysis was performed on the two variables.

[0070]

[0071] Where ρ is the Spearman correlation coefficient, which ranges from -1 to 1. ρ > 0 indicates a positive correlation between the two variables, ρ < 0 indicates a negative correlation, and ρ = 0 indicates no linear correlation between the two variables. The absolute value of the coefficient indicates the strength of the correlation; values ​​closer to 1 indicate a stronger correlation.

[0072] Example:

[0073] The monitoring object of this embodiment is the Hangzhou-Jiaxing-Huzhou Plain. The terrain of this area is a shallow saucer-shaped depression with Taihu Lake as its center, which rises in the east and south and decreases in the west and north. The cultivated land area is small and the cultivated land is seriously fragmented.

[0074] A remote sensing extraction method for cultivated land boundaries comprises the following steps:

[0075] 1) Select all high-resolution remote sensing images of a certain area in the Hangzhou-Jiaxing-Huzhou Plain in 2021, and calculate the NDVI value of each remote sensing image using red and near-infrared band data. The specific implementation process is as follows:

[0076] 11) Select all Sentinel-2 remote sensing images of a certain area in the Hangzhou-Jiaxing-Huzhou Plain in 2021;

[0077] 12) Based on the QA band of Sentinel-2 remote sensing images, calculate the percentage of clean pixels in the image, eliminate images with a clean pixel percentage of less than 99%, and retain images with a clean pixel percentage greater than 99%;

[0078] 13) Calculate the NDVI value of each remote sensing image using the 10m resolution Red and NIR bands of Sentinel-2 remote sensing images.

[0079] 2) Create a cumulative frequency map of potential cultivated land edges, such as Figure 1 As shown, the specific implementation process is as follows:

[0080] 21) Using the Canny edge detection algorithm, perform convolution calculation on each NDVI data obtained in step 1) to extract the area (edge) with grayscale mutation to form a binary image;

[0081] 22) performing equal-weighted summing and superposition processing on each binary image in step 21) to produce a potential edge frequency map;

[0082] 23) Using the cultivated land in the WorldCover product (2021) as the target land type, perform masking on the potential edge frequency map in step 22) to obtain a potential cultivated land edge cumulative frequency map.

[0083] 3) Create a stable farmland boundary map, such as Figure 2 As shown, the specific implementation process is as follows:

[0084] 31) Using the OTSU automatic threshold segmentation algorithm, the edges in the potential cultivated land edge cumulative frequency map in step 2 are divided into true edges and non-edges;

[0085] 32) For the true edge obtained in step 31), the OTSU automatic threshold segmentation algorithm is again used to perform convolution calculation to divide the true edge into permanent edges and temporary edges.

[0086] 33) By eliminating non-edges and temporary edges and retaining permanent edges, a stable farmland boundary map is obtained.

[0087] 4) Accuracy verification, such as Figure 3 As shown, the specific implementation process is as follows:

[0088] 41) Use spatial analysis tools to calculate the proportion of permanent margins per unit area of ​​cultivated land;

[0089] 42) Based on the Geo-Wiki Field Size dataset, farmland was divided into four size classes according to its ECR value within a 1600m radius grid around the sampling point using the correlation coefficient method and expert experience, with the classification thresholds being 0.074, 0.085, and 0.099, respectively.

[0090] 43) Using a confusion matrix, we analyzed the consistency between the cultivated land size predicted based on the ECR value and the cultivated land size in the Geo-Wiki Field Size dataset, and conducted a Spearman correlation analysis between the two variables. The confusion matrix results showed that the consistent areas were primarily distributed on small-scale farmland, which is consistent with the characteristics of small-scale agriculture in my country. The Spearman correlation coefficient between the farmland size prediction results based on the ECR value and the Geo-Wiki Field Size data reached 0.315, with a p value far less than 0.001, indicating a high positive correlation between the two variables. This demonstrates the feasibility and scientific validity of the present invention.

[0091] In summary, the remote sensing extraction method for cultivated land boundaries of the present invention utilizes public remote sensing data, has low computational cost, adaptive algorithm parameters, and good spatial generalization ability.

[0092] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are merely preferred examples of the present invention and are not intended to limit the present invention. Various changes and improvements may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and improvements fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A remote sensing extraction method for cultivated land boundaries, characterized in that: The following steps are involved: S1. Select high-resolution remote sensing images of the study area within a natural year and produce time-series NDVI image data within the year; S2. Processing the intra-year time series NDVI data images through edge detection, spatial overlay, cultivated land range extraction, and other land type masking to obtain a potential cultivated land edge cumulative frequency map; In step S2, based on the 10m resolution annual time-series NDVI data image obtained in step S1, an edge detection algorithm is used to identify the edges in each image; a spatial overlay method is applied to obtain the cumulative number of each edge; the land use data is used to extract the cultivated land area in the study area, and other land types are masked to obtain a potential cultivated land edge cumulative number map; The specific steps include: S21, using the Canny edge detection algorithm, performing convolution calculation on the NDVI value of each remote sensing image obtained in step S1, extracting areas with grayscale mutations, and forming a binary image; S22, performing equal-weighted summing and superposition processing on each binary image obtained in step S21 to produce a potential edge frequency map; S23, performing mask processing on the potential edge frequency map in step S22 using cultivated land in the ESA WorldCover 2021 product as the target land class to obtain a potential cultivated land edge cumulative frequency map; S3. Classifying the cultivated land edges in the potential cultivated land edge cumulative frequency map into permanent edges, temporary edges, and non-edges by an automatic threshold segmentation algorithm, retaining the permanent edges, and obtaining a cultivated land boundary map; S4. The accuracy of cultivated land boundary extraction was verified by calculating the ECR value, using confusion matrix and Spearman correlation analysis, and comparing with the Geo-Wiki Field Size dataset.

2. The remote sensing extraction method for cultivated land boundaries according to claim 1, characterized in that: In step S1, a Sentinel-2 remote sensing image within a natural year is selected, and the NDVI value of each remote sensing image is calculated using red light band and near infrared band data, specifically including the following steps: S11. Select Sentinel-2 remote sensing images of the study area within one natural year; S12. Calculate the percentage of clean pixels in the Sentinel-2 remote sensing image based on its QA bands, discard images with a clean pixel percentage less than 99%, and retain images with a clean pixel percentage greater than 99%. S13. Calculate the NDVI value of each remote sensing image obtained in step S12 using the 10m resolution Red band and NIR band in the Sentinel-2 remote sensing image. The formula is as follows: ； Where, Normalized Difference Vegetation Index (NDVI) is an important parameter that reflects crop growth and nutritional information. is the reflectance of the near-infrared band of the remote sensing image; is the reflectance of the red light band of the remote sensing image.

3. The remote sensing extraction method for cultivated land boundaries according to claim 1, characterized in that: In step S21, the threshold of the Canny edge detection algorithm is set to 100, and Sigma is set to 1.

5.

4. The remote sensing extraction method for cultivated land boundaries according to claim 1, characterized in that: The step S3 specifically includes the following steps: S31, using the OTSU automatic threshold segmentation algorithm once, dividing the edges in the potential cultivated land edge cumulative frequency map obtained in step S2 into true edges and non-edges; S32, performing convolution calculation on the true edge obtained in step 31 using the OTSU automatic threshold segmentation algorithm to divide the true edge into permanent edges and temporary edges; S33. By eliminating non-edges and temporary edges and retaining permanent edges, a stable farmland boundary map is obtained.

5. The remote sensing extraction method for cultivated land boundaries according to claim 1, characterized in that: The step S4 comprises the following steps: S41, using spatial analysis tools to calculate the permanent edge ratio per unit area of ​​cultivated land based on the stable cultivated land boundary map obtained in step S3; ； Where ECR is the cultivated land margin ratio. Ideally, the lower the ECR value, the larger the farmland area, and the smaller the permanent margin ratio. S42. Based on the Geo-Wiki Field Size dataset, within a 1600m radius grid around the sampling point, the classification threshold is determined by the correlation coefficient method and expert experience, and the farmland is divided into four size classes: L, M, S, and XS according to the ECR value of the cultivated land; S43. Using the confusion matrix, we analyzed the consistency between the cultivated land size predicted based on the ECR value and the cultivated land size in the Geo-Wiki Field Size dataset, and performed a Spearman correlation analysis on the two variables. ； Where, is the Spearman correlation coefficient, and its value range is [-1, 1]; Indicates that there is a positive correlation between two variables. Indicates negative correlation, Indicates that there is no linear correlation between the two variables; the absolute value of the coefficient indicates the strength of the correlation, and the closer the value is to 1, the stronger the correlation.

6. The remote sensing extraction method for cultivated land boundaries according to claim 5, characterized in that: In step S42, the classification thresholds of L, M, S and XS are 0.074, 0.085 and 0.099 respectively.

Images