A method and device for calculating the deployment area of a roof-mounted photovoltaic power station

Abstract

This invention discloses a method and apparatus for calculating the deployment area of ​​a rooftop solar power station. Its features include: reconstructing color components from the acquired high-resolution aerospace remote sensing image to determine a single-channel grayscale distribution map; determining edge segments from the single-channel grayscale distribution map; constructing and closing building boundaries based on physical constraints of the building's physical structure and edge pixel segments to determine the complete building pixel region; extracting the complete building pixel region using a topology deformation optimization algorithm to determine the original building pixel region; for each original building pixel region, identifying a set of subordinate obstacle regions within the original building pixel region, and performing a set difference operation based on the original building pixel region and the subordinate obstacle region set to determine the target deployment area map. This significantly improves the accuracy of the construction area calculation and enhances the operational efficiency of regional solar energy resource surveys.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, and in particular to a method and apparatus for calculating the deployment area of ​​a rooftop solar power station. Background Technology

[0002] Driven by the carbon neutrality strategy, distributed solar energy harvesting systems are rapidly becoming widespread in urban building clusters. To accurately assess the actual space available for installing solar power systems on buildings, high spatial resolution spaceborne remote sensing imagery is typically relied upon. While this imagery can capture the rooftops of urban buildings, traditional topographic analysis methods based on manually set rules or automated classification models based on deep feature learning use these rooftops as reference information for solar power station installation. However, in reality, urban buildings often have various ancillary structures or equipment, such as elevator buildings, security fences, solar water heaters, and central air conditioning units. These ancillary structures or equipment can affect the installation of solar power stations on rooftops, leading to inflated usable area calculations. Furthermore, existing technologies using empirical fixed coefficients for area estimation lack the ability to deduct specific rooftop obstacles in real-world conditions, resulting in low accuracy. Summary of the Invention

[0003] This invention provides a method and apparatus for calculating the deployment area of ​​a rooftop solar power station, thereby solving the technical problem in the prior art of accurately identifying the attached buildings on the roof of a building that divides the structure, and accurately identifying the deployment area of ​​the solar power station.

[0004] According to one aspect of the present invention, a method for calculating the deployment area of ​​a rooftop solar power station is provided, comprising: Color component reconstruction is performed on the acquired original high-resolution space remote sensing images to determine the single-channel grayscale distribution map; Edge detection is performed on the single-channel grayscale distribution image to determine at least one edge pixel segment; Based on the physical constraints of the building's physical structure and the edge pixel segments, the building boundary is constructed and closed to determine the complete building pixel region; The original building pixel region is determined by extracting the pixel region of the complete building using a topological deformation optimization algorithm. Identify the set of subordinate obstacle regions within the original building pixel region, and perform set difference operation based on the original building pixel region and the set of subordinate obstacle regions to determine the target deployment area map.

[0005] According to another aspect of the present invention, a device for calculating the deployment area of ​​a rooftop solar power station is provided, comprising: The remote sensing image processing module is used to reconstruct the color components of the acquired raw high-resolution space remote sensing images and determine the single-channel grayscale distribution map. The edge analysis module is used to determine the edges of the single-channel grayscale distribution image and identify at least one edge pixel segment. The building boundary recognition module is used to construct and close the building boundary based on the physical constraint rules of the building's physical structure and the edge pixel segments, thereby determining the complete building pixel region. The building region extraction module is used to extract the pixel region of the complete building using a topology deformation optimization algorithm to determine the original building pixel region; The deployment analysis module is used to identify the set of auxiliary obstacle regions in the original building pixel region, and perform set difference operation based on the original building pixel region and the set of auxiliary obstacle regions to determine the target deployment area map.

[0006] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the method for calculating the deployment area of ​​a rooftop solar power station according to any embodiment of the present invention.

[0007] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the method for calculating the deployment area of ​​a rooftop solar power station according to any embodiment of the present invention.

[0008] The technical solution of this invention reconstructs the color components of the acquired original high-resolution aerospace remote sensing image to determine a single-channel grayscale distribution map; it then performs edge detection on the single-channel grayscale distribution map to identify at least one edge pixel segment. Through image processing of the original high-resolution aerospace remote sensing image, it effectively preserves and extracts building edge features; based on the physical constraints of the building's physical structure and the edge pixel segment, it constructs and closes building boundaries to determine the complete building pixel region; and it uses a topology deformation optimization algorithm to extract the complete building pixel region, thus determining the original building pixel region. This achieves accurate capture of complex linear building features, thereby ensuring... The system ensures the integrity of the building's geometric outline; identifies the set of auxiliary obstacle regions within the original building's pixel area; performs set difference operations based on the original building's pixel area and the set of auxiliary obstacle regions to determine the target deployment area map; achieves pixel-level precise stripping of auxiliary obstructions; optimizes the suitable construction area; and addresses the technical problem of accurately identifying auxiliary buildings on the roof of a building in existing technologies, thus solving the problem of accurately identifying the deployment area of ​​a photovoltaic power station. By producing a practically usable geometric range, the system significantly improves the calculation accuracy of the buildable capacity of distributed photovoltaic arrays, without requiring large-scale manual intervention, greatly enhancing the operational efficiency of regional solar energy resource surveys.

[0009] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 A flowchart of a method for calculating the deployment area of ​​a rooftop solar power station is provided as an embodiment of the present invention; Figure 2 A flowchart illustrating another method for calculating the deployment area of ​​a rooftop solar power station provided in an embodiment of the present invention; Figure 3 A flowchart illustrating another method for calculating the deployment area of ​​a rooftop solar power station provided in an embodiment of the present invention; Figure 4 A schematic diagram of the structure of a rooftop solar power station deployment area calculation device provided in an embodiment of the present invention; Figure 5A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. Detailed Implementation

[0012] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0013] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0014] Figure 1 This invention provides a flowchart of a method for calculating the deployment area of ​​a rooftop solar power station. This embodiment is applicable to situations where the rooftop area suitable for deploying a solar power station is identified by analyzing high-resolution aerospace remote sensing images. This method can be executed by a rooftop solar power station deployment area calculation device, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes: S110. Reconstruct the color components of the acquired original high-resolution space remote sensing image to determine the single-channel grayscale distribution map.

[0015] Among them, the raw high-resolution images of spaceborne remote sensing can be high-resolution images acquired by image sensors carried by spacecraft. It should be noted that raw high-resolution images of spaceborne remote sensing are usually acquired by man-made spacecraft in space orbit.

[0016] Optionally, the technical solution of the present invention can not only process raw high-resolution images from aerospace remote sensing, but also high-resolution images from aerial remote sensing, such as images acquired by aircraft or drones.

[0017] Optionally, the single-channel grayscale distribution map can be a grayscale image composed of the pixel grayscale values ​​corresponding to each pixel in the original high-resolution image from aerospace remote sensing.

[0018] Optionally, atmospheric scattering and sensor photoelectric response inconsistencies can be eliminated from the original high-resolution aerospace remote sensing images, and multispectral band registration and fusion can be performed. Finally, color enhancement and balancing can be used to obtain a color aerospace remote sensing image with distinct color levels.

[0019] Optionally, each pixel in the color spaceborne remote sensing image can be calculated pixel by pixel, and each pixel can be mapped to the corresponding gray value to obtain a single-channel grayscale distribution map.

[0020] Specifically, the original high-resolution images acquired from space remote sensing are reconstructed using color components to determine the single-channel grayscale distribution map.

[0021] S120. Perform edge detection on the single-channel grayscale distribution map to determine at least one edge pixel segment.

[0022] Optionally, after obtaining the single-channel grayscale distribution image, since there is noise in the original high-resolution image of aerospace remote sensing, noise filtering is first performed on the single-channel grayscale distribution image before edge judgment. This invention filters random noise pixels in the single-channel grayscale distribution image through median filtering. For each pixel in the single-channel grayscale distribution image, a corresponding sliding window is constructed with the pixel as the center, the grayscale values ​​of the neighboring pixels of the pixel are extracted, and the grayscale value of the pixel is replaced by the median value of all pixels in the sliding window, thus completing the first noise filtering of the single-channel grayscale distribution image and obtaining the first filtered single-channel grayscale distribution image.

[0023] Optionally, the single-channel grayscale distribution image obtained from the first filtering can be further linearly filtered by performing a convolution operation on the single-channel grayscale distribution image obtained from the first filtering using a Gaussian smoothing template to reduce the negative impact of high-frequency random signals and obtain a linearly filtered single-channel grayscale distribution image.

[0024] Optionally, an edge pixel segment can be a segment of pixels that conforms to the edge of a ground object. It should be noted that edge pixel segments are used to represent potential boundary segments on the roof of a building.

[0025] Optionally, based on the linearly filtered single-channel grayscale distribution map, at least one edge pixel segment in the single-channel grayscale distribution map that is suspected to be the boundary of the building roof surface is identified, and its topological connectivity is maintained.

[0026] Specifically, edge detection is performed on the single-channel grayscale distribution map to determine at least one edge pixel segment.

[0027] S130. Based on the physical constraint rules of the building's physical structure and the edge pixel segments, construct and close the building boundary to determine the complete building pixel region.

[0028] Optionally, the physical constraint rules for the building's physical structure can be constraints composed of the physical characteristics of the building's physical structure. It should be noted that the physical constraint rules for the building's physical structure are used to identify edge pixel segments that conform to the building's physical structure. By determining whether the edge pixel segments conform to the physical constraint rules of the building's physical structure, a complete building pixel region composed of edge pixel segments is selected. This complete building pixel region can be a pixel region composed of multiple building roof surfaces.

[0029] Optionally, in a single-channel grayscale distribution map, edge pixel segments may represent the boundaries of different real-world objects, such as building edges, road edges, farmland boundaries, and fences. Each edge pixel segment can exist with at least one edge pixel segment. By analyzing the physical constraints of the building's physical structure, it can be determined whether each edge pixel segment and its adjacent edge pixel segments satisfy the building's physical structure. This results in at least one edge pixel segment that conforms to the building's physical structure. These edge pixel segments are then closed to obtain a building boundary layer composed of edge pixel segments representing the building's boundary. For example, the physical constraints of the building's physical structure could be that the edge pixel segments are rectangular edges, the edge pixel segments are parallel or perpendicular to each other, and the edge pixel segments and their adjacent edge pixel segments have closed or semi-closed contours with a aspect ratio.

[0030] Optionally, after obtaining the building boundary layer, based on the pixel position of each pixel in the edge pixel segment of the building boundary layer in the single-channel grayscale distribution map, the internal space of the building boundary layer is filled to obtain the complete building pixel area.

[0031] Specifically, building boundaries are constructed and closed based on physical constraints and edge pixel segments of the building's physical structure to determine the complete building pixel region.

[0032] S140. The pixel region of the complete building is extracted by the topology deformation optimization algorithm to determine the original building pixel region.

[0033] The original building pixel region can be a pixel region that is closed and connected by the complete building pixel region and has the top surface of the building.

[0034] Optionally, since the complete building pixel region is composed of multiple closed edge pixel segments, the boundary contour of the complete building pixel region is not smooth. The complete building pixel region is extracted by the topology deformation optimization algorithm to smooth the boundary contour of the complete building pixel region and obtain the original building pixel region.

[0035] Specifically, the original building pixel region is determined by extracting the pixel region of the complete building through a topology deformation optimization algorithm.

[0036] S150. Identify the set of subordinate obstacle regions in the original building pixel region, and perform set difference operation based on the original building pixel region and the set of subordinate obstacle regions to determine the target deployment area map.

[0037] The set of auxiliary obstacle regions can be a collection of all auxiliary obstacle regions within the original building pixel region. It should be noted that multiple auxiliary buildings or devices exist within the original building pixel region. Identifying each auxiliary building or device within the original building pixel region yields the individual auxiliary obstacle regions, thus resulting in the set of auxiliary obstacle regions.

[0038] Optionally, the target deployment area map can be an area map showing where a solar power station can be placed on the roof of a building. It should be noted that the set of auxiliary obstacle areas in the original building pixel area is removed to obtain the clearance area in the original building pixel area excluding auxiliary obstacles, and this clearance area is used as the target deployment area map of the solar power station.

[0039] Specifically, the set of subordinate obstacle regions in the original building pixel region is identified, and a set difference operation is performed based on the original building pixel region and the set of subordinate obstacle regions to determine the target deployment area map.

[0040] The technical solution of this invention reconstructs the color components of the acquired original high-resolution aerospace remote sensing image to determine a single-channel grayscale distribution map; it then performs edge detection on the single-channel grayscale distribution map to identify at least one edge pixel segment. Through image processing of the original high-resolution aerospace remote sensing image, it effectively preserves and extracts building edge features; based on the physical constraints of the building's physical structure and the edge pixel segment, it constructs and closes building boundaries to determine the complete building pixel region; and it uses a topology deformation optimization algorithm to extract the complete building pixel region, thus determining the original building pixel region. This achieves accurate capture of complex linear building features, thereby ensuring... The system ensures the integrity of the building's geometric outline; identifies the set of auxiliary obstacle regions within the original building's pixel area; performs set difference operations based on the original building's pixel area and the set of auxiliary obstacle regions to determine the target deployment area map; achieves pixel-level precise stripping of auxiliary obstructions; optimizes the suitable construction area; and addresses the technical problem of accurately identifying auxiliary buildings on the roof of a building in existing technologies, thus solving the problem of accurately identifying the deployment area of ​​a photovoltaic power station. By producing a practically usable geometric range, the system significantly improves the calculation accuracy of the buildable capacity of distributed photovoltaic arrays, without requiring large-scale manual intervention, greatly enhancing the operational efficiency of regional solar energy resource surveys.

[0041] Figure 2 This is a flowchart illustrating another method for calculating the deployment area of ​​a rooftop solar power station, provided by an embodiment of the present invention. The relationship between this embodiment and the previous embodiments is that this specifically describes the edge detection process for a single-channel grayscale distribution image. Figure 2 As shown, the method includes: S210. Reconstruct the color components of the acquired original high-resolution space remote sensing image to determine the single-channel grayscale distribution map.

[0042] S220. Calculate the gradient component for each pixel of the single-channel grayscale distribution map using the difference operator to obtain the gradient component corresponding to each pixel; calculate the gradient modulus and spatial pointing angle corresponding to each pixel for the gradient component of each pixel.

[0043] Optionally, the difference operator can be used to calculate the gradient of a single-channel grayscale distribution map. For example, the difference operator can be the Sobel operator, the Prewitt operator, the Scharr operator, or the central difference operator.

[0044] Optionally, the gradient components are the results of calculating the gradient in the horizontal and vertical directions of the pixel corresponding to the pixel position. It should be noted that the gradient components in the horizontal and vertical directions are calculated separately for each pixel of the single-channel grayscale distribution map using the difference operator, resulting in the horizontal gradient component and the vertical gradient component.

[0045] Among them, the gradient modulus is used to represent the degree of change of pixel grayscale value in a single-channel grayscale distribution map, and the spatial pointing angle is the gradient direction of the pixel in the single-channel grayscale distribution map.

[0046] Optionally, for each pixel, the gradient magnitude and spatial pointing angle corresponding to the pixel are based on the gradient components in the horizontal and vertical directions.

[0047] Specifically, the gradient component is calculated for each pixel of the single-channel grayscale distribution map using the difference operator, and the gradient component corresponding to each pixel is obtained; for the gradient component of each pixel, the gradient magnitude and spatial pointing angle corresponding to each pixel are calculated.

[0048] S230. Construct the gradient modulus map and the gradient direction map based on the gradient modulus and the spatial pointing angle corresponding to each pixel point; perform edge judgment based on the gradient modulus map and the gradient direction map to determine at least one edge pixel segment.

[0049] The gradient modulus map displays the gradient modulus at each pixel location in a single-channel grayscale distribution map, while the gradient direction map displays the gradient direction at each pixel location. It's important to note that the gradient modulus map effectively represents the edge distribution in a single-channel grayscale distribution map, and the gradient direction map effectively represents the edge direction corresponding to each pixel.

[0050] Optionally, a gradient modulus map and a gradient direction map can be constructed using the gradient modulus and spatial pointing angle corresponding to each pixel to display the edge information and edge direction present in the single-channel grayscale distribution map.

[0051] Specifically, a gradient modulus map and a gradient direction map are constructed based on the gradient modulus and spatial pointing angle corresponding to each pixel; edge detection is performed based on the gradient modulus map and the gradient direction map to determine at least one edge pixel segment.

[0052] Optionally, in another optional embodiment of the present invention, the step of determining at least one edge pixel segment based on the gradient modulus map and the gradient direction map includes: Non-maximum suppression is performed on each pixel based on the gradient modulus map and the gradient direction map to determine the gradient modulus response map; edge judgment is performed on each pixel of the gradient modulus response map through a dual threshold judgment mechanism to determine at least one edge pixel and a suspected pixel; for each edge pixel, edge tracking is performed based on the edge pixel and all the suspected pixels to determine the edge pixel segment.

[0053] Optionally, for each pixel location, when a pixel location is considered a boundary pixel location, the gradient modulus of that pixel location is usually greater than the pixel values ​​of surrounding non-boundary pixel locations. For each pixel location, non-maximum suppression is performed on the pixel location based on the gradient modulus map and gradient direction map. If a pixel location passes the maximum suppression judgment, the gradient modulus of that pixel location is not processed; if a pixel location does not pass the maximum suppression judgment, the gradient modulus of that pixel location is suppressed to obtain the gradient modulus response map.

[0054] The gradient modulus response map can be used to represent the edge pixel map composed of the gradient moduli of pixels after non-maximum suppression (NMS). It should be noted that because NMS processes the gradient moduli of non-edge pixel locations, the gradient moduli of edge pixel locations are higher in the gradient modulus response map, clearly displaying the edge information present in the single-channel grayscale distribution map.

[0055] Optionally, in the gradient modulus response map, edge pixels have higher gradient moduli. However, these edge pixels are typically discontinuous and contain some noise pixels, resulting in a chaotic distribution. A dual-threshold mechanism is used to determine the edge position of each pixel in the gradient modulus response map. If a pixel at a given position has a value greater than the higher threshold in the dual-threshold mechanism, it is considered an edge pixel. If a pixel at a given position has a value greater than the lower threshold but less than the higher threshold, it is considered a potential edge pixel. If a pixel at a given position has a value less than the lower threshold, it is considered noise and removed. The high and low thresholds can be adaptively set based on different image resolutions.

[0056] In this context, edge pixels can be understood as pixels identified as edges in the gradient modulus response map; potential pixels can be understood as pixels in the gradient modulus response map that may have the potential to be edges. It should be noted that in this invention, if a potential pixel lies within a straight line connecting at least two edge pixels, it can be identified as part of an edge; otherwise, it is considered noise.

[0057] Optionally, the edge tracking algorithm can be used to connect various edge pixels and identify edge pixel segments in the gradient modulus response map. It should be noted that when performing edge tracking, the algorithm uses the edge pixel as the starting point and performs recursive tracking. If a suspected pixel is identified and its direction is consistent with and connected to the edge pixel, then the suspected pixel is treated as an edge pixel and tracking continues; otherwise, edge tracking stops. If an edge pixel is identified, tracking continues directly; if other pixels are identified, tracking stops; if the image boundary is reached, tracking stops; and the edge pixel segment obtained from the tracked edge pixel is output. After edge tracking of all edge pixels is completed, at least one edge pixel segment is obtained in the gradient modulus response map and the single-channel grayscale distribution map.

[0058] Specifically, non-maximum suppression is performed on each pixel based on the gradient modulus map and gradient direction map to determine the gradient modulus response map; edge judgment is performed on each pixel of the gradient modulus response map through a dual threshold judgment mechanism to determine at least one edge pixel and a suspected pixel; for each edge pixel, edge tracking is performed based on the edge pixel and all suspected pixels to determine the edge pixel segment.

[0059] S240. Map the pixels corresponding to each edge pixel segment to a preset parameter space linear voting detector to construct a parameter accumulation array; determine the edge straight line trajectory corresponding to each edge pixel segment based on the significant peak points in the parameter accumulation array.

[0060] The parameter space linear voting detector can be a pre-defined discretized parameter space, and the parameter accumulation array can be a cumulative matrix obtained by mapping each pixel point to the parameter space to obtain the linear voting results. It should be noted that by mapping each edge pixel point to the pre-defined parameter space linear voting detector, identifying the edge pixel points in the parameter space, and recording the linear voting results of each edge pixel point, the parameter accumulation array is obtained.

[0061] A salient peak can be a common intersection point of multiple edge pixels in the parameter space. It should be noted that in the parametric accumulation array, there exists at least one salient peak, and each salient peak corresponds to an edge line trajectory in the image. This edge line trajectory can be a connected edge line composed of various edge pixel segments.

[0062] Specifically, the pixels corresponding to each edge pixel segment are mapped to a preset parameter space linear voting detector to construct a parameter accumulation array; based on the significant peak points in the parameter accumulation array, the edge straight line trajectory corresponding to each edge pixel segment is determined.

[0063] S250. Based on the physical constraint rules of the building's physical structure and the edge straight line trajectory, construct and close the building boundary to determine the complete building pixel region.

[0064] Optionally, after obtaining the edge straight line trajectories that exist in the single-channel grayscale distribution image, the physical constraints of the building physical structure are used to analyze each edge straight line trajectory to identify whether each edge straight line trajectory meets the building physical structure, so as to obtain at least one edge straight line trajectory that meets the building physical structure. The edge straight line trajectories are then closed to obtain a building boundary layer composed of edge straight line trajectories. Based on the pixel positions of each pixel in the edge straight line trajectory in the building boundary layer in the single-channel grayscale distribution image, the internal space is filled on the building boundary layer to obtain the complete building pixel area.

[0065] Specifically, building boundaries are constructed and closed based on physical constraints of the building's physical structure and edge straight line trajectories to determine the complete building pixel region.

[0066] Optionally, in another optional embodiment of the present invention, the construction and closure of the building boundary based on the physical constraint rules of the building's physical structure and the edge straight line trajectory to determine the complete building pixel region includes: Based on the physical constraint rules of the building's physical structure, the trajectories of each edge line are filtered to determine suspected building lines; For each suspected building line, the degree of belonging of each pixel in the single-channel grayscale distribution map to each suspected building line is identified based on the line direction of the suspected building line, and the belonging pixel point corresponding to each suspected building line is determined; Based on the corresponding pixel points of the suspected building lines, the building boundary is constructed and closed to determine the complete building pixel region.

[0067] Optionally, a suspected building line can be a trajectory line that conforms to the physical constraints of the building's physical structure. Each edge line trajectory is identified to determine whether it conforms to the physical constraints of the building's physical structure, thus obtaining at least one edge line trajectory that conforms to the building's physical structure as a suspected building line.

[0068] Optionally, for each suspected building line, the geometric slope parameter of the suspected building line can be extracted as the line direction of the suspected building line.

[0069] Optionally, for each suspected building line, a starting pixel is defined for the suspected building line, and the displacement difference between each pixel and the starting pixel of the suspected building line is calculated. This determines the degree of association between each pixel and the suspected building line, thus identifying the pixel to which each suspected building line belongs. For example, a pixel is defined as (u, v), and the starting pixel of the suspected building line is (u...v ... ref ,v ref The displacement difference is used to evaluate the degree of belonging of each pixel to the suspected building line through the recombined deviation discriminant. The specific evaluation and judgment formula is as follows: in, Represents the geometric offset. For the detected first Boundary inclination angle, This is the set upper limit for the allowable deviation.

[0070] If the geometric offset is not greater than the set upper limit of allowable deviation, the pixel is the corresponding pixel of the suspected building line; if the geometric offset is greater than the set upper limit of allowable deviation, the pixel is not the corresponding pixel of the suspected building line. The corresponding pixel is the building edge pixel along the direction of the suspected building line.

[0071] Optionally, pixel reconstruction and closure are performed on the broken or incomplete building edges based on each suspected building line and the corresponding pixel point of the suspected building line to obtain a building boundary layer with building boundaries. The internal space is filled on the building boundary layer of the building boundaries to obtain the complete building pixel area.

[0072] Specifically, based on the physical constraints of the building's physical structure, the trajectories of each edge line are filtered to identify suspected building lines. For each suspected building line, the degree of belonging of each pixel in the single-channel grayscale distribution map to each suspected building line is identified based on the line direction of the suspected building line, thus determining the corresponding pixel point of each suspected building line. Based on the corresponding pixel points of the suspected building lines, the building boundary is constructed and closed to determine the complete building pixel region.

[0073] S260. The pixel region of the complete building is extracted by the topology deformation optimization algorithm to determine the original building pixel region.

[0074] S270. Identify the set of subordinate obstacle regions in the original building pixel region, and perform set difference operation based on the original building pixel region and the set of subordinate obstacle regions to determine the target deployment area map.

[0075] This invention utilizes the synergistic effect of a multi-level gradient edge extraction algorithm and a parameter space linear voting detector to accurately capture complex linear features of buildings. For edge defects caused by light and shadow occlusion, a fitting strategy based on displacement offset residual discriminant can automatically fill in discontinuous boundary pixels, achieving intelligent reconstruction of damaged boundaries and ensuring the integrity of the building's geometric outline.

[0076] Figure 3 This is a flowchart illustrating another method for calculating the deployment area of ​​a rooftop solar power station, provided by an embodiment of the present invention. The relationship between this embodiment and the previous embodiments is that this method specifically describes the process of identifying attached obstacles. Figure 3 As shown, the method includes: S310. Reconstruct the color components of the acquired original high-resolution space remote sensing image to determine the single-channel grayscale distribution map.

[0077] S320. Calculate the gradient component for each pixel of the single-channel grayscale distribution map using the difference operator to obtain the gradient component corresponding to each pixel; calculate the gradient modulus and spatial pointing angle corresponding to each pixel for the gradient component of each pixel.

[0078] S330. Construct the gradient modulus map and the gradient direction map based on the gradient modulus and the spatial pointing angle corresponding to each pixel point; perform edge judgment based on the gradient modulus map and the gradient direction map to determine at least one edge pixel segment.

[0079] S340. Map the pixels corresponding to each edge pixel segment to a preset parameter space linear voting detector to construct a parameter accumulation array; determine the edge straight line trajectory corresponding to each edge pixel segment based on the significant peak points in the parameter accumulation array.

[0080] S350. Based on the physical constraint rules of the building's physical structure and the edge straight line trajectory, construct and close the building boundary to determine the complete building pixel region.

[0081] S360. The pixel region of the complete building is extracted using a topology deformation optimization algorithm to determine the original building pixel region.

[0082] S370. Reconstruct the center pixel value of the pixel region based on the grayscale statistical mean of pixels in each local pixel region of the original building pixel region; perform mean smoothing processing on the local pixel region based on the center pixel value of the local pixel region to determine the top background layer.

[0083] Optionally, the grayscale statistical mean can be the average of the grayscale values ​​of all pixels within the pixel locality. It should be noted that the pixel locality can be understood as multiple pixel regions divided from the original building pixel region, and the size of the pixel locality is determined by a pre-set analysis window. Mean smoothing is performed on the building's roof surface corresponding to the pixel locality using the center pixel value, eliminating high-frequency background noise caused by roof material texture and uneven lighting, generating a smoothed roof background layer. The center pixel value is used for noise removal on the building's roof surface corresponding to the pixel locality. For example, This represents the original grayscale value of the pixel. For analysis window, The formula for calculating the grayscale statistical mean M, which represents the total number of pixels contained in a local pixel area, is as follows: The top background layer can be a background layer of the building's top surface that contains only the building's top plane and any attached obstacles within the original building's pixel area. It should be noted that the smoothed top background layer clearly displays the usable planes on the building's top surface and any attached obstacles within those planes.

[0084] Specifically, the center pixel value of each pixel region is reconstructed based on the grayscale statistical mean of pixels within each local pixel region of the original building pixel area; the pixel region is then smoothed by mean based on the center pixel value to determine the top background layer.

[0085] S380. Dynamically segment the original building pixel region to determine the set of auxiliary obstacle regions corresponding to the original building pixel region; perform set difference operation based on the original building pixel region and the set of auxiliary obstacle regions to determine the target deployment area map.

[0086] Specifically, the original building pixel region is dynamically segmented to determine the set of auxiliary obstacle regions corresponding to the original building pixel region; based on the original building pixel region and the set of auxiliary obstacle regions, a set difference operation is performed to determine the target deployment area map.

[0087] Optionally, in another optional embodiment of the present invention, the step of dynamically segmenting the original building pixel region to determine the set of auxiliary obstacle regions corresponding to the original building pixel region includes: Based on a preset differential operator, convolution operations are performed on the top background layer in the horizontal and vertical directions to determine the variation intensity value; based on the variation intensity value, the obstacle edges of each auxiliary obstacle are identified; based on the second-order Laplacian differential operation, the segmented grayscale pixels of the top background layer are identified; based on the segmented grayscale pixels and the obstacle edges, the original building pixel region is dynamically segmented to determine the set of auxiliary obstacle regions.

[0088] The preset differential operator can be a pre-set value for identifying the variation intensity of obstacle edges within the top background layer. The variation intensity value can be understood as the variation intensity value of the feature gradient.

[0089] Optionally, varying the intensity value can effectively identify continuous obstacle edges in the top background layer. The obstacle edges of each individual auxiliary obstacle in the top background layer are extracted using varying intensity values.

[0090] Optionally, the second-order Laplacian derivative is used to detect local extrema of the subordinate obstacles in the top background layer, which can then be used as the segmentation grayscale pixels for dividing each subordinate obstacle. These segmentation grayscale pixels can be the most prominent pixels on the edges of the obstacles in the top background layer.

[0091] Optionally, in the top background layer, convolution operations are performed in the horizontal and vertical directions using a first-order preset differential operator to determine the variation intensity value of the top background layer, identify the obstacle edges of each auxiliary obstacle in the top background layer, identify the segmented grayscale pixels of the obstacle edges in the top background layer using Laplacian second-order differential operations, dynamically segment the original building pixel area based on each grayscale pixel and each obstacle edge, extract the pixel area corresponding to each auxiliary obstacle, obtain each auxiliary obstacle area, and determine the set of auxiliary obstacle areas.

[0092] Optionally, after obtaining the segmented grayscale pixels, the optimal threshold is calculated by using Laplacian second-order differential operation and further recursively. The optimal threshold and the edges of each obstacle are used to dynamically segment the original building pixel area, extract the pixel area corresponding to each auxiliary obstacle, obtain each auxiliary obstacle area, and determine the set of auxiliary obstacle areas.

[0093] Specifically, based on a preset differential operator, convolution operations are performed on the top background layer in the horizontal and vertical directions to determine the variation intensity value; based on the variation intensity value, the obstacle edges of each auxiliary obstacle are identified; based on the second-order Laplacian differential operation, the segmented grayscale pixels of the top background layer are identified; based on the segmented grayscale pixels and obstacle edges, the original building pixel area is dynamically segmented to determine the set of auxiliary obstacle areas.

[0094] For example, in this invention, Used to describe the grayscale values ​​of segmented grayscale pixels calculated iteratively; the optimal threshold is obtained through... The calculation process of the recursive optimization method is shown below: in, For smoothing correction factor; It can be a threshold correction increment, used to represent the adjustment method and magnitude of recursive optimization.

[0095] The original building pixel region is dynamically segmented based on the optimal threshold to obtain a set of auxiliary obstacle regions. This set of auxiliary obstacle regions is then processed using R... obs To represent, through R total The original building pixel region is represented by a set difference operation performed on the set of the original building pixel region and the set of attached obstacle regions to obtain the target deployment area map. The target deployment area map is obtained through W. eff The specific process of set difference operation is as follows: In this embodiment of the invention, by guiding the calculation of second-order differential extrema and dynamic step-iteration thresholds, it is possible to accurately locate ancillary obstacles such as air conditioning units, ventilation structures, and elevator shafts from complex building roof backgrounds. Through refined segmentation methods, inaccurate construction range estimations caused by neglecting roof obstacles are avoided. Pixel-level precise stripping of ancillary obstructions is achieved, optimizing the suitable construction area. The actual usable geometric range is directly generated through set difference operations, significantly improving the calculation accuracy of the constructable capacity of distributed photoelectric arrays. This invention allows for flexible adaptation to remote sensing backgrounds of different resolutions and architectural styles, requiring no large-scale manual intervention throughout the entire process, greatly improving the operational efficiency of regional solar energy resource surveys.

[0096] Figure 4 This is a schematic diagram of a device for calculating the deployment area of ​​a rooftop solar power station, provided as an embodiment of the present invention. Figure 4 As shown, the device includes: a remote sensing image processing module 410, an edge analysis module 420, a building boundary recognition module 430, a building region extraction module 440, and a deployment analysis module 440; wherein, The remote sensing image processing module 410 is used to reconstruct the color components of the acquired original high-resolution space remote sensing images and determine the single-channel grayscale distribution map. Edge analysis module 420 is used to perform edge judgment on the single-channel grayscale distribution map and determine at least one edge pixel segment; The building boundary recognition module 430 is used to construct and close the building boundary based on the physical constraint rules of the building's physical structure and the edge pixel segments, and to determine the complete building pixel region. The building region extraction module 440 is used to extract the pixel region of the complete building through a topology deformation optimization algorithm to determine the original building pixel region; The deployment analysis module 450 is used to identify the set of subordinate obstacle regions in the original building pixel region, and perform set difference operation based on the original building pixel region and the set of subordinate obstacle regions to determine the target deployment area map.

[0097] The technical solution of this invention reconstructs the color components of the acquired original high-resolution aerospace remote sensing image to determine a single-channel grayscale distribution map; it then performs edge detection on the single-channel grayscale distribution map to identify at least one edge pixel segment. Through image processing of the original high-resolution aerospace remote sensing image, it effectively preserves and extracts building edge features; based on the physical constraints of the building's physical structure and the edge pixel segment, it constructs and closes building boundaries to determine the complete building pixel region; and it uses a topology deformation optimization algorithm to extract the complete building pixel region, thus determining the original building pixel region. This achieves accurate capture of complex linear building features, thereby ensuring... The system ensures the integrity of the building's geometric outline; identifies the set of auxiliary obstacle regions within the original building's pixel area; performs set difference operations based on the original building's pixel area and the set of auxiliary obstacle regions to determine the target deployment area map; achieves pixel-level precise stripping of auxiliary obstructions; optimizes the suitable construction area; and addresses the technical problem of accurately identifying auxiliary buildings on the roof of a building in existing technologies, thus solving the problem of accurately identifying the deployment area of ​​a photovoltaic power station. By producing a practically usable geometric range, the system significantly improves the calculation accuracy of the buildable capacity of distributed photovoltaic arrays, without requiring large-scale manual intervention, greatly enhancing the operational efficiency of regional solar energy resource surveys.

[0098] Optionally, the deployment analysis module 450 is specifically used for: The center pixel value of the pixel region is reconstructed based on the grayscale statistical mean of pixels within each pixel region of the original building pixel region; The pixel locality is smoothed by mean value processing based on the center pixel value of the pixel locality to determine the top background layer; The original building pixel region is dynamically segmented to determine the set of auxiliary obstacle regions corresponding to the original building pixel region.

[0099] Optionally, the deployment analysis module 450 is further configured to: Based on a preset differential operator, the top background layer is convolved in both the horizontal and vertical directions to determine the variation intensity value; The obstacle edges of each auxiliary obstacle are identified based on the varying intensity values; The segmented grayscale pixels of the top background layer are identified based on the second-order Laplace derivative operation; The original building pixel region is dynamically segmented based on the segmented grayscale pixels and the obstacle edges to determine the set of auxiliary obstacle regions.

[0100] Optionally, the building boundary recognition module 430 is specifically used for: The pixels corresponding to each edge pixel segment are mapped to a preset parameter space linear voting detector to construct a parameter accumulation array; Based on the significant peak points in the parametric accumulation array, the edge straight line trajectory corresponding to each edge pixel segment is determined; Based on the physical constraints of the building's physical structure and the edge straight line trajectory, the building boundary is constructed and closed to determine the pixel region of the complete building.

[0101] Optionally, the building boundary recognition module 430 is further used for: Based on the physical constraint rules of the building's physical structure, the trajectories of each edge line are filtered to determine suspected building lines; For each suspected building line, the degree of belonging of each pixel in the single-channel grayscale distribution map to each suspected building line is identified based on the line direction of the suspected building line, and the belonging pixel point corresponding to each suspected building line is determined; Based on the corresponding pixel points of the suspected building lines, the building boundary is constructed and closed to determine the complete building pixel region.

[0102] Optionally, the edge analysis module 420 is specifically used for: The gradient component is calculated for each pixel of the single-channel grayscale distribution map using the difference operator, and the gradient component corresponding to each pixel is obtained. For each pixel, calculate the gradient magnitude and spatial pointing angle corresponding to each pixel for the gradient component; The gradient modulus map and the gradient direction map are constructed based on the gradient modulus and the spatial pointing angle corresponding to each pixel. Edge detection is performed based on the gradient modulus map and the gradient direction map to determine at least one edge pixel segment.

[0103] Optionally, the edge analysis module 420 is further configured to: Based on the gradient modulus map and the gradient direction map, non-maximum suppression is performed on each pixel to determine the gradient modulus response map; The gradient modulus response map is edge-determined by a dual threshold determination mechanism to identify at least one edge pixel and one suspected pixel. For each edge pixel, the edge pixel segment is determined by performing edge tracking based on the edge pixel and all the suspected pixels using an edge tracking algorithm.

[0104] The rooftop solar power station deployment area calculation device provided in this embodiment of the invention can execute the rooftop solar power station deployment area calculation method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0105] Figure 5 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their patterns are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0106] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0107] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of monitors, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer grids such as the Internet and / or various telecommunications grids.

[0108] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the method for calculating the deployment area of ​​a rooftop solar power station.

[0109] In some embodiments, the method for calculating the deployment area of ​​a rooftop solar power station can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the method for calculating the deployment area of ​​a rooftop solar power station described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the method for calculating the deployment area of ​​a rooftop solar power station by any other suitable means (e.g., by means of firmware).

[0110] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0111] Computer programs used to implement the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the patterns / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0112] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0113] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0114] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or grid browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication grid). Examples of communication grids include local area networks (LANs), wide area networks (WANs), blockchain grids, and the Internet.

[0115] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS servers, such as high management difficulty and weak business scalability.

[0116] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0117] This embodiment provides a computer-readable storage medium storing a computer program thereon. When executed by a processor, the program implements the steps of the method for calculating the deployment area of ​​a rooftop solar power station as provided in any embodiment of the present invention. The method includes: Color component reconstruction is performed on the acquired original high-resolution space remote sensing images to determine the single-channel grayscale distribution map; Edge detection is performed on the single-channel grayscale distribution image to determine at least one edge pixel segment; Based on the physical constraints of the building's physical structure and the edge pixel segments, the building boundary is constructed and closed to determine the complete building pixel region; The original building pixel region is determined by extracting the pixel region of the complete building using a topological deformation optimization algorithm. Identify the set of subordinate obstacle regions within the original building pixel region, and perform set difference operation based on the original building pixel region and the set of subordinate obstacle regions to determine the target deployment area map.

[0118] The computer storage medium of this invention can be any combination of one or more computer-readable media. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0119] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0120] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0121] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of mesh, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0122] Those skilled in the art will understand that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a grid of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby allowing them to be stored in a storage device for execution by a computing device, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0123] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0124] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for calculating the deployment area of ​​a rooftop solar power station, characterized in that, include: Color component reconstruction is performed on the acquired original high-resolution space remote sensing images to determine the single-channel grayscale distribution map; Edge detection is performed on the single-channel grayscale distribution image to determine at least one edge pixel segment; Based on the physical constraints of the building's physical structure and the edge pixel segments, the building boundary is constructed and closed to determine the complete building pixel region; The original building pixel region is determined by extracting the pixel region of the complete building using a topological deformation optimization algorithm. Identify the set of subordinate obstacle regions within the original building pixel region, and perform set difference operation based on the original building pixel region and the set of subordinate obstacle regions to determine the target deployment area map.

2. The method according to claim 1, characterized in that, The set of subordinate obstacle regions identified in the original building pixel region includes: The center pixel value of the pixel region is reconstructed based on the grayscale statistical mean of pixels within each pixel region of the original building pixel region; The pixel locality is smoothed by mean value processing based on the center pixel value of the pixel locality to determine the top background layer; The original building pixel region is dynamically segmented to determine the set of auxiliary obstacle regions corresponding to the original building pixel region.

3. The method according to claim 2, characterized in that, The step of dynamically segmenting the original building pixel region to determine the set of associated obstacle regions corresponding to the original building pixel region includes: Based on a preset differential operator, the top background layer is convolved in both the horizontal and vertical directions to determine the variation intensity value; The obstacle edges of each auxiliary obstacle are identified based on the varying intensity values; The segmented grayscale pixels of the top background layer are identified based on the second-order Laplace derivative operation; The original building pixel region is dynamically segmented based on the segmented grayscale pixels and the obstacle edges to determine the set of auxiliary obstacle regions.

4. The method according to claim 1, characterized in that, The construction and closure of building boundaries based on the physical constraints of the building's physical structure and the edge pixel segments, determining the complete building pixel region, includes: The pixels corresponding to each edge pixel segment are mapped to a preset parameter space linear voting detector to construct a parameter accumulation array; Based on the significant peak points in the parametric accumulation array, the edge straight line trajectory corresponding to each edge pixel segment is determined; Based on the physical constraints of the building's physical structure and the edge straight line trajectory, the building boundary is constructed and closed to determine the pixel region of the complete building.

5. The method according to claim 4, characterized in that, The construction and closure of building boundaries based on the physical constraints of the building's physical structure and the edge straight line trajectory, determining the complete building pixel region, includes: Based on the physical constraint rules of the building's physical structure, the trajectories of each edge line are filtered to determine suspected building lines; For each suspected building line, the degree of belonging of each pixel in the single-channel grayscale distribution map to each suspected building line is identified based on the line direction of the suspected building line, and the belonging pixel point corresponding to each suspected building line is determined; Based on the corresponding pixel points of the suspected building lines, the building boundary is constructed and closed to determine the complete building pixel region.

6. The method according to claim 1, characterized in that, The step of edge detection of the single-channel grayscale distribution map to determine at least one edge pixel segment includes: The gradient component is calculated for each pixel of the single-channel grayscale distribution map using the difference operator, and the gradient component corresponding to each pixel is obtained. For each pixel, calculate the gradient magnitude and spatial pointing angle corresponding to each pixel for the gradient component; A gradient modulus map and a gradient direction map are constructed based on the gradient modulus and spatial pointing angle corresponding to each pixel. Edge detection is performed based on the gradient modulus map and the gradient direction map to determine at least one edge pixel segment.

7. The method according to claim 6, characterized in that, The step of determining at least one edge pixel segment based on the gradient modulus map and the gradient direction map includes: Based on the gradient modulus map and the gradient direction map, non-maximum suppression is performed on each pixel to determine the gradient modulus response map; The gradient modulus response map is edge-determined by a dual threshold determination mechanism to identify at least one edge pixel and one suspected pixel. For each edge pixel, the edge pixel segment is determined by performing edge tracking based on the edge pixel and all the suspected pixels using an edge tracking algorithm.

8. A device for calculating the deployment area of ​​a rooftop solar power station, characterized in that, include: The remote sensing image processing module is used to reconstruct the color components of the acquired raw high-resolution space remote sensing images and determine the single-channel grayscale distribution map. The edge analysis module is used to determine the edges of the single-channel grayscale distribution image and identify at least one edge pixel segment. The building boundary recognition module is used to construct and close the building boundary based on the physical constraint rules of the building's physical structure and the edge pixel segments, thereby determining the complete building pixel region. The building region extraction module is used to extract the pixel region of the complete building using a topology deformation optimization algorithm to determine the original building pixel region; The deployment analysis module is used to identify the set of auxiliary obstacle regions in the original building pixel region, and perform set difference operation based on the original building pixel region and the set of auxiliary obstacle regions to determine the target deployment area map.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the method for calculating the deployment area of ​​a rooftop solar power station according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the method for calculating the deployment area of ​​the rooftop solar power station as described in any one of claims 1-7.

Images