Land consolidation boundary line division method and system based on machine vision

Abstract

The invention relates to the technical field of remote sensing image processing, in particular to a land consolidation boundary line division method and system based on machine vision. The method comprises the following steps: obtaining a plurality of superpixel blocks of a satellite remote sensing image; according to the elevation information distribution of different pixel points in each super-pixel block in the digital elevation model, obtaining the terrain height change degree of each super-pixel block; according to the elevation information difference between each pixel point in each super-pixel block and other pixel points in the corresponding neighborhood range in the digital elevation model and the gradient distribution of the corresponding pixel points in different directions in the digital elevation model, obtaining the overall water flow direction value of each super-pixel block; further obtaining the merging possibility between different super-pixel blocks; and obtaining a superpixel optimal block, and dividing the arrangement boundary line of the to-be-divided land region. According to the method, the superpixel segmentation process of the land region to be divided is accurately obtained, so that the accuracy of boundary line division arrangement is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of remote sensing image processing, and particularly relates to a method and system for dividing the boundary line of land consolidation based on machine vision. Background Art

[0002] By clearly dividing the boundary line of land consolidation in a region, it helps to reasonably arrange the spatial layout of cultivated land and other types of land in mountainous areas, clarify the scope of land for different uses, improve the quality of cultivated land, increase the effective cultivated land area, and improve the agricultural ecological conditions and ecological environment; therefore, in order to realize the rational utilization and sustainable development of land resources, it is necessary to carry out land consolidation and optimal allocation.

[0003] In the prior art, the superpixel segmentation technology is used to divide the satellite remote sensing images of mountainous land by function, and the superpixels are merged and adjusted to change the morphological scale of the land; however, due to the complex mountain terrain, large slope changes, and uncertain undulations, only analyzing the satellite remote sensing images without considering the land slope and land suitability results in a large error in the division of the consolidation boundary. Summary of the Invention

[0004] In order to solve the technical problem that only analyzing the satellite remote sensing images without considering the land slope and land suitability results in a large error in the division of the consolidation boundary, the purpose of the present invention is to provide a method and system for dividing the boundary line of land consolidation based on machine vision, and the specific technical solutions adopted are as follows:

[0005] The present invention proposes a method for dividing the boundary line of land consolidation based on machine vision, and the method includes:

[0006] Obtain the satellite remote sensing image, spectral image, and digital elevation model of the land area to be divided;

[0007] Obtain multiple superpixel blocks of the satellite remote sensing image according to the spectral characteristics of each pixel point on the spectral image and the color characteristics on the satellite remote sensing image;

[0008] Obtain the terrain height change degree of each superpixel block according to the elevation information distribution of different pixel points in each superpixel block in the digital elevation model; obtain the local water flow direction value of each pixel point in each superpixel block according to the elevation information difference between each pixel point in each superpixel block and other pixel points within the corresponding neighborhood range in the digital elevation model; obtain the overall water flow direction value of each superpixel block according to the local water flow direction values of different pixel points in each superpixel block and the gradient distribution of the corresponding pixel points in different directions in the digital elevation model;

[0009] Obtain the merging possibility between different superpixel blocks according to the terrain height change degree and the overall water flow direction value between different superpixel blocks;

[0010] Obtain the optimal superpixel blocks according to the merging possibility between all superpixel blocks, and divide the sorting boundary line of the land area to be divided.

[0011] Further, the method for obtaining the superpixel blocks includes:

[0012] Obtain the vegetation performance degree of each pixel point according to the spectral characteristics of each pixel point in the spectral image and the color characteristics on the satellite remote sensing image;

[0013] Use the superpixel segmentation algorithm to obtain multiple equal-width superpixel initial blocks of the satellite remote sensing image;

[0014] Obtain the performance difference between the vegetation performance degrees of each pixel point and the central pixel point within each superpixel initial block; if the performance difference is greater than the preset difference threshold, calculate the relative distance between the corresponding pixel point and the central pixel points of other superpixel blocks, and select the other superpixel block with the smallest relative distance as the new superpixel initial block where each pixel point is located until the performance differences corresponding to the pixel points within all superpixel initial blocks are not greater than the preset difference threshold, so as to obtain multiple superpixel blocks.

[0015] Further, the method for obtaining the vegetation performance degree includes:

[0016] Obtain the NDVI vegetation coverage factor of each pixel point based on the spectral image; obtain the color components of each pixel point in the RGB space of the remote sensing image;

[0017] Obtain the product of the NDVI vegetation coverage factor and the color component of each pixel point as the vegetation performance degree of each pixel point.

[0018] Further, the method for obtaining the terrain height change degree includes:

[0019] Obtain the mean value of the differences in elevation information in the digital elevation model between the central pixel point and all other pixel points within each superpixel block as the first height coefficient;

[0020] Obtain the mean value of the differences in elevation information in the digital elevation model between different pixel points within each superpixel block as the second height coefficient;

[0021] Obtain the product between the first height coefficient and the second height coefficient within each superpixel block as the terrain height change degree of each superpixel block.

[0022] Further, the method for obtaining the local water flow direction value includes:

[0023] For any superpixel block, obtain the elevation information difference between each pixel point and every other pixel point within the neighborhood range in the digital elevation model;

[0024] Select the maximum value of the elevation information differences between each pixel point and all other pixel points within the neighborhood range as the local water flow direction value of each pixel point.

[0025] Furthermore, the method for obtaining the overall water flow direction value includes:

[0026] Obtain the elevation gradient of each pixel point in the east-west direction in the digital elevation model as the first gradient; obtain the elevation gradient of each pixel point in the north-south direction in the digital elevation model as the second gradient;

[0027] Obtain the ratio of the second gradient to the first gradient and perform a negative correlation mapping as the elevation slope between pixel points; calculate the elevation slope using the arctangent function as the first direction coefficient of each pixel point;

[0028] Obtain the cumulative value of the product between the local water flow direction values of different pixel points and the corresponding first direction coefficients of the pixel points as the overall water flow direction value within each superpixel block.

[0029] Furthermore, the method for obtaining the merging possibility includes:

[0030] Construct a two-dimensional row vector from the terrain height change degree and the overall water flow direction value of each superpixel block;

[0031] Obtain the cosine similarity of the corresponding row vectors between each superpixel block and every other superpixel block; obtain the relative distance of the central pixel points between each superpixel block and every other superpixel block;

[0032] Obtain the ratio between the cosine similarity and the relative distance between each superpixel block and every other superpixel block as the merging possibility between each superpixel block and every other superpixel block.

[0033] Furthermore, the method for obtaining the optimal superpixel block includes:

[0034] Judge whether the superpixel blocks need to be merged according to the merging possibilities between all superpixel blocks; if it is judged that merging is needed, obtain new superpixel blocks until it is judged that no merging is needed to obtain the optimal superpixel block.

[0035] Furthermore, the method for judging whether the superpixel blocks need to be merged according to the merging possibilities between all superpixel blocks includes:

[0036] If the merging possibility between all superpixel blocks is greater than a preset merging threshold, it is determined to merge the corresponding superpixel blocks.

[0037] The present invention also provides a land consolidation boundary line division system based on machine vision, including a memory, a processor, and a computer program stored in the memory and operable on the processor. When the processor executes the computer program, the steps of any one of the methods for dividing the land consolidation boundary line based on machine vision are implemented.

[0038] The present invention has the following beneficial effects:

[0039] According to the spectral characteristics of each pixel point on the spectral image and the color characteristics on the satellite remote sensing image, the present invention obtains multiple superpixel blocks of the satellite remote sensing image, reduces the complexity of subsequent processing, and at the same time retains the local details of the image; according to the elevation information distribution of different pixel points in each superpixel block in the digital elevation model, the present invention obtains the terrain height change degree of each superpixel block, reflecting the terrain undulation within the block; according to the elevation information difference between each pixel point in each superpixel block and other pixel points within the corresponding neighborhood range in the digital elevation model, the present invention obtains the local water flow direction value of each pixel point within each superpixel block, the local hydrological characteristics of the ground surface; according to the local water flow direction values of different pixel points within each superpixel block and the gradient distribution of the corresponding pixel points in different directions in the digital elevation model, the present invention obtains the overall water flow direction value of each superpixel block, comprehensively calculates the local water flow direction value and the elevation gradient, and calculates the overall water flow direction value of each superpixel block, reflecting the hydrological characteristics and terrain characteristics within the block; according to the terrain height change degree and the overall water flow direction value between different superpixel blocks, the present invention obtains the merging possibility between different superpixel blocks, determines which blocks can be merged into a larger area, and obtains the optimal superpixel blocks according to the merging possibility between all superpixel blocks, for dividing the consolidation boundary line of the land area to be divided. The present invention improves the accuracy of dividing the consolidation boundary line by accurately obtaining the superpixel segmentation process of the land area to be divided. Description of the Drawings

[0040] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0041] Figure 1 It is a flowchart of a method for dividing the land consolidation boundary line based on machine vision provided by an embodiment of the present invention;

[0042] Figure 2 Flowchart of a method for obtaining the possibility of merging provided by an embodiment of the present invention. Detailed implementation manner

[0043] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following, in combination with the accompanying drawings and preferred embodiments, details a method and system for dividing the boundary line of land consolidation based on machine vision according to the present invention, including its specific implementation manner, structure, features and effects. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0044] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0045] The following specifically describes the specific solution of a method and system for dividing the boundary line of land consolidation based on machine vision provided by the present invention with reference to the accompanying drawings.

[0046] Please refer to Figure 1 , which shows a flowchart of a method for dividing the boundary line of land consolidation based on machine vision provided by an embodiment of the present invention, specifically including:

[0047] Step S1: Obtain the satellite remote sensing image, spectral image, and digital elevation model of the land area to be divided.

[0048] In the embodiment of the present invention, for a single-source remote sensing image of a mountainous complex terrain, superpixel segmentation only uses each component in the color space, and may not be able to accurately capture the local texture features of the image when facing complex terrains, especially terrain changes such as slopes and vegetation cover. Therefore, it is necessary to collect and analyze the feature information of multiple parts of the image; first, use a satellite remote sensing device to obtain a high-resolution optical image of the land area to be divided, that is, a satellite remote sensing image; select a drone equipped with a high-resolution camera and a lidar device to obtain the standard three-dimensional point cloud data and spectral image of the land area to be divided; among them, the three-dimensional point cloud data is processed by the inverse distance weighted method to generate a high-precision digital elevation model for analysis to reflect the terrain features of the land area. Obtain the satellite remote sensing image, spectral image, and digital elevation model of the land area to be divided.

[0049] It should be noted that, in the embodiments of the present invention, noise removal, radiometric correction, etc. are performed on satellite remote sensing images and spectral images to ensure data quality, and the image data is unified into a raster format; the DEM data is used as one layer, and the spectral image is used as another layer, and geometric registration methods are used to fuse the spatial data with the satellite remote sensing image of the corresponding size, which helps to analyze local details such as spectral information and topographic information.

[0050] Step S2: Obtain multiple superpixel blocks of the satellite remote sensing image according to the spectral characteristics of each pixel point in the spectral image and the color characteristics on the satellite remote sensing image.

[0051] In the satellite remote sensing image, green represents strong vegetation coverage, and terraced fields usually have artificial management landforms and low vegetation coverage.

[0052] Preferably, in an embodiment of the present invention, the method for obtaining superpixel blocks includes:

[0053] Obtain the vegetation expression degree of each pixel point according to the spectral characteristics of each pixel point in the spectral image and the color characteristics on the satellite remote sensing image;

[0054] Preferably, in an embodiment of the present invention, the method for obtaining the vegetation expression degree includes:

[0055] Obtain the NDVI vegetation coverage factor of each pixel point based on the spectral image; obtain the color components of each pixel point in the RGB space of the remote sensing image;

[0056] Obtain the product of the NDVI vegetation coverage factor and the color component of each pixel point as the vegetation expression degree of each pixel point.

[0057] It should be noted that, in other embodiments of the present invention, other basic mathematical operations such as addition can also be used to achieve a positive correlation relationship, and the specific means are well-known technical means to those skilled in the art and will not be elaborated here.

[0058] Obtain multiple initial superpixel blocks of equal width in size of the satellite remote sensing image by using a superpixel segmentation algorithm;

[0059] Obtain the performance difference of the vegetation expression degree between each pixel point and the central pixel point within each initial superpixel block; if the performance difference is greater than a preset difference threshold, calculate the relative distance between the corresponding pixel point and the central pixel point of other superpixel blocks, and select the other superpixel block with the smallest relative distance as the new initial superpixel block where each pixel point is located until the performance differences corresponding to the pixel points within all initial superpixel blocks are not greater than the preset difference threshold, and obtain multiple superpixel blocks.

[0060] Based on this, for the performance difference corresponding to a pixel point being greater than a preset difference threshold, the initial superpixel block where the pixel point is located will be updated, that is, a new initial superpixel block will be obtained for the analysis of the performance difference corresponding to the pixel point, until the performance differences corresponding to the pixel points within all the initial superpixel blocks are not greater than the preset difference threshold, then stop adjusting the initial superpixel block where the pixel point is located, and obtain the final superpixel block for analysis.

[0061] It should be noted that in the embodiment of the present invention, the segmentation quantity is set to 1500, and a plurality of initial superpixel blocks with equal width in size of the satellite remote sensing image are obtained by using a superpixel segmentation algorithm. The relative distance between the central pixel points of the initial superpixel blocks is S; among them, the relative distance between pixel points can be obtained by using existing distance calculation methods such as calculating the Euclidean distance or Manhattan distance between the position coordinates of pixel points. The specific means are well-known technical means to those skilled in the art and will not be elaborated here.

[0062] It should be noted that in one embodiment of the present invention, the size of the preset difference threshold is 0.75; in other embodiments of the present invention, the size of the preset difference threshold is a well-known technical means to those skilled in the art and will not be limited and elaborated here.

[0063] Step S3: According to the elevation information distribution of different pixel points in each superpixel block in the digital elevation model, obtain the terrain height change degree of each superpixel block; according to the elevation information difference between each pixel point in each superpixel block and other pixel points within the corresponding neighborhood range in the digital elevation model, obtain the local water flow direction value of each pixel point in each superpixel block; according to the local water flow direction values of different pixel points in each superpixel block and the gradient distribution of the corresponding pixel points in different directions in the digital elevation model, obtain the overall water flow direction value of each superpixel block.

[0064] Since the terrain undulation change difference of mountains is relatively large, in order to prevent a large amount of soil erosion during the farming process in different regions, the terraced fields are usually reclaimed in the regions with relatively gentle altitude changes, and there is a relatively uniform change in height information between different plots, while the original vegetation shows a chaotic terrain height distribution. Therefore, analyze the terrain height change degree of each sub-block area; according to the elevation information distribution of different pixel points in each superpixel block in the digital elevation model, obtain the terrain height change degree of each superpixel block.

[0065] Preferably, in one embodiment of the present invention, the method for obtaining the terrain height change degree includes:

[0066] Obtain the difference mean value of the elevation information between the central pixel point and all other pixel points in each superpixel block in the digital elevation model as the first height coefficient;

[0067] Obtain the average difference in elevation information in the digital elevation model between different pixel points within each superpixel block as the second height coefficient;

[0068] Obtain the product between the first height coefficient and the second height coefficient within each superpixel block as the terrain height change degree of each superpixel block.

[0069] In an embodiment of the present invention, the formula for the terrain height change degree is expressed as:

[0070]

[0071] where h i represents the terrain height change degree of the i-th superpixel block; Z i represents the elevation information of the central pixel point in the i-th superpixel block in the digital elevation model; Z i,j represents the elevation information of the j-th other pixel point in the i-th superpixel block in the digital elevation model; represents the average difference in elevation information in the digital elevation model between different pixel points within the i-th superpixel block, that is, the second height coefficient; n represents the number of pixel points in the i-th superpixel block.

[0072] In the formula for the terrain height change degree, represents calculating the average difference in elevation information in the digital elevation model between the central pixel point and all other pixel points within the i-th superpixel block, that is, the first height coefficient. The greater the difference in elevation information, the greater the undulation degree between pixel points, the greater the second height coefficient, and the greater the difference in elevation information between different pixel points, the greater the terrain change degree.

[0073] The water flow path determines the flow direction of water on the ground surface. During the design process of converting sloping land into terraced fields, terraced fields are usually on flat slopes, while there are more significant slope changes in unsuitable planting areas. If the water flow path is ignored when merging superpixel blocks, it may lead to poor water flow in the merged area, unable to improve agricultural production efficiency, and even cause problems such as soil erosion. Therefore, according to the difference in elevation information in the digital elevation model between each pixel point within each superpixel block and other pixel points within the corresponding neighborhood range, obtain the local water flow direction value of each pixel point within each superpixel block.

[0074] Preferably, in an embodiment of the present invention, the method for obtaining the local water flow direction value includes:

[0075] For any superpixel block, obtain the difference in elevation information in the digital elevation model between each pixel point and each other pixel point within the neighborhood range;

[0076] Select the maximum value of the elevation information difference between each pixel and all other pixels within the neighborhood range as the local water flow direction value of each pixel.

[0077] It should be noted that in an embodiment of the present invention, the neighborhood range is a range centered on each pixel and composed of pixels in 8 adjacent directions. In other embodiments of the present invention, the size of the neighborhood range can be specifically set according to specific circumstances, and no limitation and elaboration are made here.

[0078] The gradient can reflect the elevation change rate in different directions and is used to describe the water flow direction value or terrain features. According to the local water flow direction values of different pixels within each superpixel block and the gradient distribution of the corresponding pixels in different directions in the digital elevation model, the overall water flow direction value of each superpixel block is obtained.

[0079] Preferably, in an embodiment of the present invention, the method for obtaining the overall water flow direction value includes:

[0080] Obtain the elevation gradient of each pixel in the east-west direction in the digital elevation model as the first gradient; obtain the elevation gradient of each pixel in the north-south direction in the digital elevation model as the second gradient;

[0081] Obtain the ratio of the second gradient to the first gradient and perform a negative correlation mapping as the elevation slope between pixels; use the arctangent function to calculate the elevation slope as the first direction coefficient of each pixel;

[0082] Obtain the cumulative value of the product between the local water flow direction values of different pixels and the first direction coefficients of the corresponding pixels as the overall water flow direction value within each superpixel block.

[0083] In an embodiment of the present invention, the formula for the overall water flow direction value is expressed as:

[0084]

[0085] where γ i represents the overall water flow direction value within the i-th superpixel block; γ i,j is the water flow direction value of the j-th pixel within the i-th superpixel block; represents the elevation gradient of the j-th pixel in the east-west direction in the digital elevation model; represents the elevation gradient of the j-th pixel in the north-south direction in the digital elevation model; arctan() represents the arctangent function.

[0086] In the formula for the water flow direction value, It represents analyzing the differences in elevation gradients of each pixel in different directions in the digital elevation model, obtaining the elevation gradient of each pixel in the east-west direction in the digital elevation model as the first gradient; obtaining the elevation gradient of each pixel in the north-south direction in the digital elevation model as the second gradient; obtaining the ratio of the second gradient to the first gradient and performing a negative correlation mapping, that is, the elevation slope between pixels. It represents calculating the elevation slope using the arctangent function as the first direction coefficient of each pixel, reflecting the slope orientation of the pixel. The larger the first direction coefficient, the larger the slope, the larger the local water flow direction value, and the larger the overall water flow direction value.

[0087] Step S4: Obtain the merging possibility between different superpixel blocks according to the terrain height change degree and the overall water flow direction value between different superpixel blocks.

[0088] Adjacent superpixel blocks may have similar terrain, hydrological or spectral characteristics, but are divided into different blocks. The greater the similarity and the closer the distance, the more they need to be merged.

[0089] Preferably, in an embodiment of the present invention, for the method of obtaining the merging possibility, please refer to Figure 2 which shows a flowchart of a method for obtaining the merging possibility, including:

[0090] Step S201: Construct a two-dimensional row vector from the terrain height change degree and the overall water flow direction value of each superpixel block.

[0091] The terrain height change degree is an important parameter describing the terrain undulation degree, which can reflect the complexity and diversity of the terrain; the water flow path determines the water flow direction on the ground surface. Combining the water flow direction value parameter with the terrain height change degree can construct a more complete terrain-water system feature description system, which helps to deeply understand the terrain and water flow characteristics of the region.

[0092] Step S202: Obtain the cosine similarity of the corresponding row vectors between each superpixel block and each other superpixel block; obtain the relative distance between the central pixel points of each superpixel block and each other superpixel block.

[0093] The cosine similarity measures the similarity degree of the row vectors between superpixel blocks, that is, the similarity of the terrain and water flow in the land area. The greater the cosine similarity, the more similar the terrain and water flow, and the more likely to be merged; superpixel blocks with relatively close relative distances are closer in space, so the possibility of their merging is also higher. By analyzing the cosine similarity and the relative distance, it helps to merge the adjacent and visually similar regions in space, thus maintaining the local coherence of the image.

[0094] It should be noted that in an embodiment of the present invention, the relative distance can be obtained according to existing distance calculation methods such as the Euclidean distance or Manhattan distance between calculated position coordinates. The specific means are well-known technical means to those skilled in the art and will not be elaborated herein.

[0095] Step S203: Obtain the ratio between the cosine similarity and the relative distance between each superpixel block and each other superpixel block as the merging possibility between each superpixel block and each other superpixel block.

[0096] In an embodiment of the present invention, the formula for the merging possibility is expressed as:

[0097]

[0098] where S i,w represents the merging possibility between the w-th superpixel block and the i-th superpixel block; D i represents the row vector corresponding to the i-th superpixel block; l i represents the central coordinate of the w-th superpixel block; D w represents the row vector corresponding to the w-th superpixel block; l w represents the two-dimensional coordinate in the w-th superpixel block; cos() represents the cosine function.

[0099] In the formula for the merging possibility, cos(D i , D w ) represents calculating the cosine similarity between the corresponding row vectors of the w-th superpixel block and the i-th superpixel block. The greater the cosine similarity, the more similar the corresponding row vectors, the more consistent the terrain and water flow conditions, and the more likely they are to be merged; the closer the relative distance, the more adjacent the superpixel blocks, and the greater the merging possibility.

[0100] Step S5: Obtain the optimal superpixel blocks according to the merging possibilities between all superpixel blocks, and divide the sorting boundary line of the land area to be divided.

[0101] The merging possibility analyzes features such as terrain height parameters and overall water flow direction values between blocks to determine whether they should be merged into a larger area. The greater the merging possibility, the more likely they are to be merged, which can better reflect the actual land use units and terrain features and better support land sorting and planning work.

[0102] Preferably, in an embodiment of the present invention, the method for obtaining the optimal superpixel blocks includes:

[0103] Determine whether the superpixel blocks need to be merged according to the merging possibility between all superpixel blocks; if it is determined that merging is required, obtain new superpixel blocks until it is determined that merging is not required to obtain the optimal superpixel blocks.

[0104] Preferably, in an embodiment of the present invention, the obtaining method for determining whether the superpixel blocks need to be merged according to the merging possibility between all superpixel blocks includes:

[0105] If the merging possibility between all superpixel blocks is greater than a preset merging threshold, determine to merge the corresponding superpixel blocks.

[0106] It should be noted that, in an embodiment of the present invention, the size of the preset merging threshold is 0.8; in other embodiments of the present invention, the size of the preset merging threshold can be specifically set according to specific circumstances, and no limitation and elaboration are made here.

[0107] It should be noted that, in another embodiment of the present invention, after obtaining the optimal superpixel blocks, the division of the sorting boundary line of the land area to be divided includes: extracting the edge lines of the optimal superpixel blocks, if there are unclosed areas, using the polygon filling algorithm to detect the boundaries of the unclosed areas, automatically expanding the boundary lines to make them closed, and calculating the topological consistency of the closed areas to verify the integrity of the divided areas, and finally obtaining a relatively accurate area boundary. The boundary line of the land area to be divided must meet the requirements of geometric integrity and logical correctness, including boundary closure, no self-intersection, no overlap, no hanging lines, and area integrity, etc. The specific means are well-known technical means to those skilled in the art and will not be elaborated here.

[0108] In summary, the present invention obtains multiple superpixel blocks of the satellite remote sensing image according to the spectral characteristics of each pixel point on the spectral image and the color characteristics on the satellite remote sensing image; obtains the terrain height change degree of each superpixel block according to the elevation information distribution of different pixel points in each superpixel block in the digital elevation model; obtains the overall water flow direction value of each superpixel block according to the elevation information difference between each pixel point in each superpixel block and other pixel points within the corresponding neighborhood range in the digital elevation model, and the gradient distribution of the corresponding pixel point in different directions in the digital elevation model; and then obtains the merging possibility between different superpixel blocks; obtains the optimal superpixel blocks, and divides the sorting boundary line of the land area to be divided. The present invention improves the accuracy of the sorting boundary line division by accurately obtaining the superpixel segmentation process of the land area to be divided.

[0109] The present invention also provides a land consolidation boundary line division system based on machine vision, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of any one of the land consolidation boundary line division methods based on machine vision are implemented.

[0110] It should be noted that the above-mentioned order of the embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0111] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. A method for dividing the boundary line of land consolidation based on machine vision, characterized in that, The method includes: Obtaining a satellite remote sensing image, a spectral image, and a digital elevation model of the land area to be divided; Obtaining a plurality of superpixel blocks of the satellite remote sensing image according to the spectral characteristics of each pixel point on the spectral image and the color characteristics on the satellite remote sensing image; Obtaining the terrain height change degree of each superpixel block according to the elevation information distribution of different pixel points in each superpixel block in the digital elevation model; obtaining the local water flow direction value of each pixel point in each superpixel block according to the elevation information difference between each pixel point in each superpixel block and other pixel points within the corresponding neighborhood range in the digital elevation model; obtaining the overall water flow direction value of each superpixel block according to the local water flow direction values of different pixel points in each superpixel block and the gradient distribution of the corresponding pixel points in different directions in the digital elevation model; Obtaining the merging possibility between different superpixel blocks according to the terrain height change degree and the overall water flow direction value between different superpixel blocks; Obtaining the optimal superpixel blocks according to the merging possibility between all superpixel blocks, and dividing the overall boundary line of the land area to be divided.

2. The method for dividing the boundary line of land consolidation based on machine vision according to claim 1, characterized in that The method for obtaining the superpixel blocks includes: Obtaining the vegetation expression degree of each pixel point according to the spectral characteristics of each pixel point in the spectral image and the color characteristics on the satellite remote sensing image; Obtaining a plurality of initial superpixel blocks with equal width in size of the satellite remote sensing image by using a superpixel segmentation algorithm; Obtaining the expression difference of the vegetation expression degree between each pixel point and the central pixel point within each initial superpixel block; if the expression difference is greater than a preset difference threshold, calculating the relative distance between the corresponding pixel point and the central pixel points of other superpixel blocks, and selecting the other superpixel block corresponding to the minimum relative distance as the new initial superpixel block where each pixel point is located until the expression differences corresponding to the pixel points within all initial superpixel blocks are not greater than the preset difference threshold, thereby obtaining a plurality of superpixel blocks.

3. The method for dividing the boundary line of land consolidation based on machine vision according to claim 2, wherein The method for obtaining the vegetation expression degree includes: Obtaining the NDVI vegetation coverage factor of each pixel point based on the spectral image; obtaining the color components of each pixel point in the RGB space of the remote sensing image; Obtaining the product of the NDVI vegetation coverage factor and the color components of each pixel point as the vegetation expression degree of each pixel point.

4. A method for dividing the boundary line of land consolidation based on machine vision according to claim 1, characterized in that, The method for obtaining the terrain height change degree includes: Obtaining the average value of the elevation information differences between the central pixel point and all other pixel points within each superpixel block in the digital elevation model as the first height coefficient; Obtaining the average value of the elevation information differences between different pixel points within each superpixel block in the digital elevation model as the second height coefficient; Obtaining the product between the first height coefficient and the second height coefficient within each superpixel block as the terrain height change degree of each superpixel block.

5. A method for dividing the boundary line of land consolidation based on machine vision according to claim 1, characterized in that, The method for obtaining the local water flow direction value includes: For any superpixel block, obtaining the elevation information difference between each pixel point and each other pixel point within the neighborhood range in the digital elevation model; Select the maximum value of the elevation information difference between each pixel and all other pixels within the neighborhood range as the local water flow direction value of each pixel.

6. The method for dividing the boundary line of land consolidation based on machine vision according to claim 1, characterized in that The method for obtaining the overall water flow direction value includes: Obtain the elevation gradient of each pixel in the east-west direction in the digital elevation model as the first gradient; obtain the elevation gradient of each pixel in the north-south direction in the digital elevation model as the second gradient. Obtain the ratio of the second gradient to the first gradient and perform a negative correlation mapping as the elevation slope between pixels; calculate the elevation slope using the arctangent function as the first direction coefficient of each pixel. Obtain the cumulative value of the product between the local water flow direction values of different pixels and the first direction coefficients of the corresponding pixels as the overall water flow direction value within each superpixel block.

7. A method for dividing the boundary line of land consolidation based on machine vision according to claim 1, characterized in that, The method for obtaining the merging possibility includes: Construct a two-dimensional row vector from the terrain height change degree and the overall water flow direction value of each superpixel block. Obtain the cosine similarity of the corresponding row vectors between each superpixel block and each other superpixel block; obtain the relative distance between the central pixels of each superpixel block and each other superpixel block. Obtain the ratio between the cosine similarity and the relative distance between each superpixel block and each other superpixel block as the merging possibility between each superpixel block and each other superpixel block.

8. A method for dividing the boundary line of land consolidation based on machine vision according to claim 1, characterized in that, The method for obtaining the optimal superpixel block includes: Judge whether the superpixel blocks need to be merged according to the merging possibilities between all superpixel blocks; if it is judged that merging is required, obtain new superpixel blocks until it is judged that no merging is required to obtain the optimal superpixel block.

9. The method for dividing the boundary line of land consolidation based on machine vision according to claim 8, wherein, The method for judging whether the superpixel blocks need to be merged according to the merging possibilities between all superpixel blocks includes: If the merging possibilities between all superpixel blocks are greater than the preset merging threshold, judge to merge the corresponding superpixel blocks.

10. A land consolidation boundary line division system based on machine vision, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method for dividing the land consolidation boundary line based on machine vision according to any one of claims 1 to 9.

Images