A method and apparatus for registering water conservancy engineering drawings and remote sensing images

Abstract

This invention discloses a method and apparatus for registering water conservancy engineering drawings with remote sensing images. The method includes: extracting features from the remote sensing image to obtain water body feature data, and splitting the water body feature data into first data, second data, and third data according to a preset ratio; determining the water conservancy engineering area in the first data based on feature points of the water conservancy engineering drawing, and cropping the water conservancy engineering area from the second data and the third data respectively to obtain second region data and third region data within the corresponding region; extracting a first coordinate set of feature points matching the water conservancy engineering drawing from the second region data, and then determining feature point data within a preset range of each coordinate in the first coordinate set in the third region data, and combining them to obtain a second coordinate set; registering the water conservancy engineering drawing based on the second coordinate set and writing coordinate information, which can quickly, accurately, and in large quantities register water conservancy engineering drawings.

Description

Technical Field

[0001] This invention belongs to the field of water conservancy engineering technology, specifically relating to a method and apparatus for registering water conservancy engineering drawings and remote sensing images. Background Technology

[0002] Currently, water conservancy projects typically use CAD software or other software to create engineering drawings. The coordinate systems used are not national geodetic coordinates or internationally accepted geographic coordinates. Furthermore, for ease of production, water conservancy engineering drawings are often cropped, rotated, and scaled to accommodate construction areas, making it impossible to directly and accurately integrate with other business data. In addition, most water conservancy projects were constructed a long time ago, resulting in incomplete original data, missing measurement point information, and some projects only having paper engineering drawings. This poses significant challenges to water conservancy project data management and the construction of engineering informatization.

[0003] In existing technologies, the registration of water conservancy engineering drawings typically involves manual registration. This method involves visually matching selected feature points on the drawing and marking them on the corresponding locations in the remote sensing image. Then, specialized software is used to translate, rotate, and scale the drawing, thus achieving registration between the water conservancy engineering drawings and the features in the remote sensing image. However, existing technologies heavily rely on human experience, require a high level of skill, and face significant challenges in feature point matching, consuming substantial human, material, and time resources.

[0004] Therefore, how to quickly and accurately register water conservancy engineering drawings is a technical problem that needs to be solved by those skilled in the art. Summary of the Invention

[0005] The purpose of this invention is to solve the technical problem that the registration of water conservancy engineering drawings and remote sensing images in the prior art relies heavily on manual labor, resulting in excessively high labor and time costs.

[0006] To achieve the above-mentioned technical objectives, on the one hand, the present invention provides a method for registering hydraulic engineering drawings and remote sensing images, the method comprising:

[0007] Water body feature data is obtained by extracting features from remote sensing images, and the water body feature data is split into first data, second data and third data according to a preset ratio. The data range of the third data is larger than the data range of the second data, and the data range of the second data is larger than the data range of the first data.

[0008] Based on the feature points of the water conservancy engineering drawings, the water conservancy engineering area is determined in the first data, and based on the water conservancy engineering area, the second area data and the third area data of the corresponding area are obtained by cropping from the second data and the third data respectively.

[0009] In the second region data, a first set of coordinates of feature points matching the water conservancy engineering drawings is extracted. Then, feature point data within a preset range of each coordinate in the first set of coordinates is determined in the third region data, and they are combined to obtain a second set of coordinates.

[0010] The water conservancy engineering drawings are registered and the coordinate information is written based on the second coordinate set.

[0011] Furthermore, the determination of the water conservancy project area based on feature points from the water conservancy project drawings in the first data specifically includes:

[0012] A local window is generated, and the local window is moved within the first data and corner points are detected;

[0013] The water conservancy project area is determined by the corner points.

[0014] Furthermore, the corner point is specifically determined by the following formula:

[0015] ;

[0016] In the formula, This refers to the grayscale changes that occur when a local window is panned. This represents the pixel distance the local window moves horizontally. This represents the pixel distance the local window moves in the vertical direction. For a local window The pixel value at the specified coordinates after the local window has moved. For a local window Pixel value at coordinates For a local window Position weight at coordinates.

[0017] Furthermore, the step of extracting the first set of coordinates of feature points matching the water conservancy engineering drawings from the second region data specifically includes:

[0018] Candidate feature points in the second region data were identified, and the FAST score of each candidate feature point was calculated.

[0019] Based on the FAST score, candidate feature points are filtered to obtain filtered feature points, and the coordinates of the filtered feature points are combined into a first coordinate set.

[0020] Furthermore, the step of filtering candidate feature points based on the FAST score to obtain filtered feature points specifically includes:

[0021] If there is only one candidate feature point in the neighborhood of the preset size of the candidate feature point to be screened, then the candidate feature point is retained as the screened feature point.

[0022] If there are at least two candidate feature points within the preset size neighborhood of the candidate feature points to be screened, then the candidate feature point with the highest FAST score within the preset size neighborhood is retained and used as the screened feature point.

[0023] Furthermore, the FAST score is specifically determined using the following formula:

[0024] ;

[0025] In the formula, The FAST score of the candidate feature points. This refers to the grayscale values ​​of all surrounding pixels within a preset range of the center pixel. For the target pixel grayscale value, To determine the conditions, This represents the grayscale value of the current pixel. These are dynamic parameters.

[0026] Furthermore, the process of registering the water conservancy engineering drawings based on the second coordinate set and writing coordinate information specifically includes:

[0027] The water conservancy engineering drawings are registered based on the second coordinate set;

[0028] Write the registered water conservancy engineering drawings into a coordinate system consistent with the water body characteristic data;

[0029] Two coordinates are randomly selected from the second coordinate set, and the coordinate information is calculated by the distance between the selected two coordinates and the preset pixels in the registered water conservancy engineering drawing. The coordinate information specifically includes the horizontal coordinate of the preset pixel, the x-axis resolution of the preset pixel, the horizontal rotation coefficient, the vertical coordinate of the preset pixel, the y-axis resolution of the preset pixel, and the vertical rotation coefficient.

[0030] The coordinate information is written into the registered water conservancy engineering drawings.

[0031] On the other hand, the present invention also provides a device for registering water conservancy engineering drawings and remote sensing images, the device comprising:

[0032] The extraction module is used to extract features from remote sensing images to obtain water body feature data, and to split the water body feature data into first data, second data and third data according to a preset ratio. The data range of the third data is greater than the data range of the second data, and the data range of the second data is greater than the data range of the first data.

[0033] The trimming module is used to determine the water conservancy project area in the first data based on the feature points of the water conservancy project drawings, and to trim the water conservancy project area in the second data and the third data respectively to obtain the second area data and the third area data within the corresponding area.

[0034] The matching module is used to extract a first set of coordinates of feature points that match the water conservancy engineering drawings from the second area data, and then determine the feature point data within a preset range of each coordinate in the first set of coordinates in the third area data, and combine them to obtain a second set of coordinates.

[0035] The registration module is used to register the water conservancy engineering drawings based on the second coordinate set and write the coordinate information.

[0036] This invention provides a method and apparatus for registering water conservancy engineering drawings with remote sensing images. Compared with existing technologies, this method first extracts features from the remote sensing image to obtain water body feature data, and then splits the water body feature data into first data, second data, and third data according to a preset ratio. The data range of the third data is larger than that of the second data, and the data range of the second data is larger than that of the first data. Based on the feature points of the water conservancy engineering drawing, the water conservancy engineering area is determined in the first data, and based on the water conservancy engineering area, second region data and third region data within the corresponding region are obtained by cropping from the second data and the third data, respectively. A first coordinate set of feature points matching the water conservancy engineering drawing is extracted from the second region data, and then feature point data within a preset range of each coordinate in the first coordinate set is determined in the third region data, and these are combined to obtain a second coordinate set. Based on the second coordinate set, the water conservancy engineering drawing is registered and the coordinate information is written, which can quickly, accurately, and in large quantities register water conservancy engineering drawings. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 The diagram shown is a flowchart illustrating the registration method between water conservancy engineering drawings and remote sensing images provided in the embodiments of this specification.

[0039] Figure 2 The diagram shown is a structural schematic of the water conservancy engineering drawing and remote sensing image registration device provided in the embodiments of this specification. Detailed Implementation

[0040] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0041] like Figure 1 The diagram illustrates a flowchart of the method for registering water conservancy engineering drawings and remote sensing images provided in the embodiments of this specification. Although this specification provides the method operation steps or device structure shown in the following embodiments or figures, based on convention or without creative effort, the method or device may include more or fewer operation steps or module units after partial merging. In steps or structures where there is no necessary causal relationship in logic, the execution order of these steps or the module structure of the device are not limited to the execution order or module structure shown in the embodiments or figures of this specification. When the method or module structure is applied in actual devices, servers, or terminal products, it can be executed sequentially or in parallel according to the method or module structure shown in the embodiments or figures (e.g., in a parallel processor or multi-threaded processing environment, or even in a distributed processing or server cluster implementation environment).

[0042] The method for registering water conservancy engineering drawings and remote sensing images provided in the embodiments of this specification can be applied to terminal devices such as client and server devices, such as... Figure 1 As shown, the method specifically includes the following steps:

[0043] Step S101: Extract features from the remote sensing image to obtain water body feature data, and split the water body feature data into first data, second data and third data according to a preset ratio. The data range of the third data is larger than the data range of the second data, and the data range of the second data is larger than the data range of the first data.

[0044] Specifically, this involves acquiring remote sensing images of the areas where water conservancy projects are located, as shown in water conservancy engineering drawings. This includes acquiring multi-band remote sensing image data, such as Landsat 8-9 and Sentinel 2. Then, based on the type of area where the water project is located, a suitable water index extraction algorithm is selected. For urban areas, the MNDWI algorithm is chosen to exclude the influence of buildings; for mountainous areas, the NDWI algorithm is chosen to exclude the influence of vegetation. Remote sensing data areas are often large. For example, a Landsat 8 image ranges from 170*180km to approximately 30,600km², while a typical medium-sized irrigation area ranges from 10,000 to 300,000 mu (approximately 66,700-200km²). Directly using the raw water data for calculations would severely reduce computational efficiency. Therefore, the extracted water data needs to be converted to different resolutions for different applications. Thus, the water data is split into first, second, and third data according to a preset ratio. In specific application scenarios, these correspond to 1 / 6, 1 / 3, and 3-layer pyramid data of the original, respectively.

[0045] More specifically, the original 1 / 6 and 1 / 3 ratios refer to image compression of the actual size of the water body feature data by one-sixth and one-third, respectively. This is because the single image data of remote sensing images is large. For example, the original data size of a single Landsat 8 image is 7711x7851. The image is too large to quickly locate the area where the engineering drawing is located. Therefore, the water conservancy project area is first located according to the 1 / 6 compressed data (size is 1285*1308) (at this time, multiple candidate areas may appear). Then, the water conservancy project area is further confirmed within the candidate areas according to the 1 / 3 compressed data (size is 2570*2617) (since the rivers, lakes, etc. where the water conservancy project is located are large, the accurate location can generally be located at this time).

[0046] Step S102: Based on the feature points of the water conservancy engineering drawings, determine the water conservancy engineering area in the first data, and based on the water conservancy engineering area, respectively cut out the second area data and the third area data within the corresponding area from the second data and the third data.

[0047] In this embodiment of the application, the step of determining the water conservancy project area in the first data based on feature points of the water conservancy project drawings specifically includes:

[0048] A local window is generated, and the local window is moved to detect corner points in the first data.

[0049] The water conservancy project area is determined by the corner points.

[0050] The corner point is specifically determined by the following formula:

[0051] ;

[0052] In the formula, This refers to the grayscale changes that occur when a local window is panned. This represents the pixel distance the local window moves horizontally. This represents the pixel distance the local window moves in the vertical direction. For a local window The pixel value at the specified coordinates after the local window has moved. For a local window Pixel value at coordinates For a local window Position weight at coordinates.

[0053] The core of corner detection is to move a local window across the image and determine if there are significant changes in grayscale. If the grayscale values ​​within the window change significantly, then a corner exists in the area where the window is located. Corner detection is performed on the first data, i.e., the extracted 1 / 6 scale water body information data. Corner detection can quickly extract feature points that match those in the water conservancy engineering drawings, i.e., find the salient feature points in the drawings. Through these salient feature points, feature matching is performed. When a water body area matches the height of a corner point on the engineering drawing, the water conservancy engineering area can be determined, thus determining the extent of the engineering drawing area on the image, including the coordinates of the four bounding rectangles: XMIN, YMIN, XMAX, and YMAX. After determining the extent of the engineering area, the extracted second data, i.e., the extracted 1 / 3 scale water body information data, is cropped to obtain the data within the engineering area, i.e., the second area data. Similarly, the third data is processed in the same way to obtain the third area data.

[0054] Step S103: Extract the first set of coordinates of feature points that match the water conservancy engineering drawings from the second area data, then determine the feature point data within a preset range of each coordinate in the first set of coordinates in the third area data, and combine them to obtain the second set of coordinates.

[0055] In this embodiment of the application, the step of extracting the first set of coordinates of feature points matching the water conservancy engineering drawings from the second area data specifically includes:

[0056] Candidate feature points in the second region data were identified, and the FAST score of each candidate feature point was calculated.

[0057] Based on the FAST score, candidate feature points are filtered to obtain filtered feature points, and the coordinates of the filtered feature points are combined into a first coordinate set.

[0058] The process of filtering candidate feature points based on the FAST score to obtain filtered feature points specifically includes:

[0059] If there is only one candidate feature point in the neighborhood of the preset size of the candidate feature point to be screened, then the candidate feature point is retained as the screened feature point.

[0060] If there are at least two candidate feature points within the preset size neighborhood of the candidate feature points to be screened, then the candidate feature point with the highest FAST score within the preset size neighborhood is retained and used as the screened feature point.

[0061] Specifically, the second region data is obtained by cropping the third region data. Since the first region data has already identified multiple water conservancy project areas, the second region data mainly uses the Feature from accelerated segment test (FAST) algorithm to filter the multiple water conservancy project areas identified in the first region data to determine the final confirmed water conservancy project areas.

[0062] The FAST score is determined using the following formula:

[0063] ;

[0064] In the formula, The FAST score of the candidate feature points. This refers to the grayscale values ​​of all surrounding pixels within a preset range of the center pixel. For the target pixel grayscale value, To determine the conditions, This represents the grayscale value of the current pixel. The FAST feature point detection algorithm uses dynamic parameters. In practice, it calculates the FAST score for multiple candidate feature points within a neighborhood centered on feature point p, and retains the feature point with the highest score.

[0065] After the above processing, a first coordinate set is obtained. Then, feature point data within a preset range for each coordinate in the third region data is determined, thus obtaining a second coordinate set. The actual coordinate point is the same coordinate point, but the second coordinate set has added feature point data compared to the first coordinate set. The feature points are identified by constructing the image Hessian matrix to identify potential scale- and selection-invariant feature points. Then, the feature points are filtered and the coordinates are located. Then, the direction and invariance requirements of the feature points are obtained. Finally, a feature vector is generated and used as the feature point data.

[0066] Step S104: Register the water conservancy engineering drawings based on the second coordinate set and write the coordinate information.

[0067] In this embodiment of the application, the step of registering the water conservancy engineering drawings based on the second coordinate set and writing coordinate information specifically includes:

[0068] The water conservancy engineering drawings are registered based on the second coordinate set;

[0069] Write the registered water conservancy engineering drawings into a coordinate system consistent with the water body characteristic data;

[0070] Two coordinates are randomly selected from the second coordinate set, and the coordinate information is calculated by the distance between the selected two coordinates and the preset pixels in the registered water conservancy engineering drawing. The coordinate information specifically includes the horizontal coordinate of the preset pixel, the x-axis resolution of the preset pixel, the horizontal rotation coefficient, the vertical coordinate of the preset pixel, the y-axis resolution of the preset pixel, and the vertical rotation coefficient.

[0071] The coordinate information is written into the registered water conservancy engineering drawings.

[0072] Specifically, registration involves locating key points in engineering drawings that do not contain geographic coordinates to their corresponding geographic coordinate systems through the matching of key points. Based on the preceding process, the matching of key feature points in the water conservancy engineering drawings with water body data feature points extracted from remote sensing images has been completed, obtaining the correspondence between the feature point coordinates of the engineering drawings and the actual geographic coordinates. Registration is based on a second coordinate set, where the engineering drawings are processed through rotation, stretching, deformation, etc., to ensure that each feature point matches the actual geographic coordinates. Then, two coordinates are arbitrarily selected from the second coordinate set, and their distances to preset pixels in the registered water conservancy engineering drawings are used to calculate coordinate information. This coordinate information specifically includes the x-coordinate of the preset pixel, the x-axis resolution of the preset pixel, the horizontal rotation coefficient, the y-coordinate of the preset pixel, the y-axis resolution of the preset pixel, and the vertical rotation coefficient. This coordinate information is then written into the registered water conservancy engineering drawings.

[0073] Based on the above-described method for registering water conservancy engineering drawings and remote sensing images, one or more embodiments of this specification also provide a platform or terminal for registering water conservancy engineering drawings and remote sensing images. This platform or terminal may include devices, software, modules, plug-ins, servers, clients, etc., using the methods described in the embodiments of this specification, combined with necessary hardware implementation. Based on the same innovative concept, the systems in one or more embodiments provided in this specification are as described in the following embodiments. Since the implementation schemes and methods for solving the system problem are similar, the specific system implementation in the embodiments of this specification can refer to the implementation of the aforementioned methods. Repeated details will not be repeated. The terms "unit" or "module" used below can refer to a combination of software and / or hardware that achieves a predetermined function. Although the systems described in the following embodiments are preferably implemented in software, hardware implementation, and a combination of software and hardware, are also possible and contemplated.

[0074] Specifically, Figure 2 This is a schematic diagram of the module structure of one embodiment of the water conservancy engineering drawing and remote sensing image registration device provided in this specification, as shown below. Figure 2 As shown, the device for registering hydraulic engineering drawings and remote sensing images provided in this specification includes:

[0075] Extraction module 201 is used to extract features from remote sensing images to obtain water body feature data, and to split the water body feature data into first data, second data and third data according to a preset ratio, wherein the data range of the third data is greater than the data range of the second data, and the data range of the second data is greater than the data range of the first data.

[0076] The trimming module 202 is used to determine the water conservancy project area in the first data based on the feature points of the water conservancy project drawing, and to trim the second area data and the third area data in the second data and the third data respectively based on the water conservancy project area.

[0077] The matching module 203 is used to extract a first set of coordinates of feature points that match the water conservancy engineering drawings from the second area data, and then determine the feature point data within a preset range of each coordinate in the first set of coordinates in the third area data, and combine them to obtain a second set of coordinates.

[0078] The registration module 204 is used to register the water conservancy engineering drawings based on the second coordinate set and write the coordinate information.

[0079] It should be noted that the system described above may include other implementation methods based on the description of the corresponding method embodiments. The specific implementation methods can be referred to the description of the corresponding method embodiments above, and will not be elaborated here.

[0080] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0081] The methods or apparatus described in the embodiments provided in this specification can implement business logic through a computer program and record it on a storage medium. The storage medium can be read and executed by a computer to achieve the effects of the solutions described in the embodiments of this specification, such as:

[0082] Water body feature data is obtained by extracting features from remote sensing images, and the water body feature data is split into first data, second data and third data according to a preset ratio. The data range of the third data is larger than the data range of the second data, and the data range of the second data is larger than the data range of the first data.

[0083] Based on the feature points of the water conservancy engineering drawings, the water conservancy engineering area is determined in the first data, and based on the water conservancy engineering area, the second area data and the third area data of the corresponding area are obtained by cropping from the second data and the third data respectively.

[0084] In the second region data, a first set of coordinates of feature points matching the water conservancy engineering drawings is extracted. Then, feature point data within a preset range of each coordinate in the first set of coordinates is determined in the third region data, and they are combined to obtain a second set of coordinates.

[0085] The water conservancy engineering drawings are registered and the coordinate information is written based on the second coordinate set.

[0086] The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or plug-ins may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or other forms.

[0087] These computer program instructions can also be loaded onto a computer or other programmable resource data updating device, causing a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable device for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0088] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, system embodiments are basically similar to method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments. In the description of this specification, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this specification. Specific features, structures, materials, or characteristics described in this specification can be combined in any suitable manner in one or more embodiments or examples. Furthermore, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0089] Those skilled in the art will recognize that the embodiments described herein are intended to help the reader understand the principles of the invention, and should be understood that the scope of protection of the invention is not limited to such specific statements and embodiments. Those skilled in the art can make various other specific modifications and combinations based on the technical teachings disclosed in this invention without departing from the spirit of the invention, and these modifications and combinations are still within the scope of protection of this invention.

Claims

1. A method for registering a hydraulic engineering drawing with a remote sensing image, characterized in that, The method comprises: feature extraction is performed on a remote sensing image to obtain water body feature data, and the water body feature data is split according to a preset proportion to obtain first data, second data and third data, the data range of the third data is greater than that of the second data, and the data range of the second data is greater than that of the first data; a water conservancy project region is determined in the first data based on feature points of a water conservancy project drawing, and second region data and third region data in the corresponding regions are cut out in the second data and the third data based on the water conservancy project region; a first coordinate set of feature points matched with the water conservancy project drawing is extracted in the second region data, and then feature point data within a preset range of each coordinate in the first coordinate set is determined in the third region data, and the feature point data is combined to obtain a second coordinate set; the water conservancy project drawing is registered based on the second coordinate set and coordinate information is written; wherein the water conservancy project region is determined in the first data based on feature points of the water conservancy project drawing, and specifically comprises: a local window is generated, and the local window is moved in the first data and corner points are detected; the water conservancy project region is determined through the corner points; wherein the first coordinate set of feature points matched with the water conservancy project drawing is extracted in the second region data, and specifically comprises: candidate feature points in the second region data are determined, and a FAST score value of each candidate feature point is calculated; the candidate feature points are screened based on the FAST score value to obtain screened feature points, and coordinates of the screened feature points are combined into the first coordinate set; wherein the water conservancy project drawing is registered based on the second coordinate set and coordinate information is written, and specifically comprises: the water conservancy project drawing is registered based on the second coordinate set; the registered water conservancy project drawing is written into a coordinate system consistent with the water body feature data; two coordinates are randomly selected from the second coordinate set, and coordinate information is calculated through distances between the selected two coordinates and preset pixels in the registered water conservancy project drawing, the coordinate information specifically comprises a horizontal coordinate of the preset pixel, an x-axis direction resolution of the preset pixel, a horizontal rotation coefficient, a vertical coordinate of the preset pixel, a y-axis direction resolution of the preset pixel, and a vertical rotation coefficient; the coordinate information is written into the registered water conservancy project drawing.

2. The method of claim 1, wherein, The corner points are specifically determined by the following formula: ； In the formula, This refers to the grayscale changes that occur when a local window is panned. This represents the pixel distance the local window moves horizontally. This represents the pixel distance the local window moves in the vertical direction. For a local window The pixel value at the specified coordinates after the local window has moved. For a local window Pixel value at coordinates For a local window Position weight at coordinates.

3. The method of claim 1, wherein, The candidate feature points are screened based on the FAST score value to obtain screened feature points, and specifically comprises: if there is only one candidate feature point in a preset size neighborhood of the candidate feature point to be screened, the candidate feature point is retained as a screened feature point; if there are at least two candidate feature points in the preset size neighborhood of the candidate feature point to be screened, the candidate feature point with the highest FAST score value in the preset size neighborhood is retained and used as a screened feature point.

4. The method of registering a hydraulic engineering drawing with a remote sensing image according to claim 3, wherein, The FAST score value is specifically determined by the following formula: ； In the formula, a FAST score value of a candidate feature point, a gray value of all peripheral pixel points in a preset range of the center pixel point, a target pixel gray value, a judgment condition, a gray value of the current pixel point, a dynamic parameter.

5. A device for registering a hydraulic engineering drawing with a remote sensing image, characterized in that The device comprises: The extraction module is configured to extract features of the remote sensing image to obtain water body feature data, and split the water body feature data according to a preset proportion to obtain first data, second data and third data, wherein a data range of the third data is greater than a data range of the second data, and the data range of the second data is greater than a data range of the first data; The cropping module is configured to determine a water conservancy engineering region in the first data based on feature points of the water conservancy engineering drawing, and crop the second data and the third data based on the water conservancy engineering region to obtain second region data and third region data in the corresponding regions, respectively; The matching module is configured to extract a first coordinate set of feature points matched with the water conservancy engineering drawing from the second region data, and then determine feature point data within a preset range of each coordinate in the first coordinate set from the third region data, and combine the feature point data to obtain a second coordinate set; The registration module is configured to register the water conservancy engineering drawing based on the second coordinate set and write coordinate information; The water conservancy engineering region is determined in the first data based on the feature points of the water conservancy engineering drawing, specifically including: generating a local window, moving the local window in the first data and detecting a corner point; determining the water conservancy engineering region through the corner point; The first coordinate set of feature points matched with the water conservancy engineering drawing is extracted from the second region data, specifically including: determining candidate feature points in the second region data, and calculating a FAST score value of each candidate feature point; screening the candidate feature points based on the FAST score value to obtain screened feature points, and combining coordinates of the screened feature points into the first coordinate set; The water conservancy engineering drawing is registered based on the second coordinate set, and the coordinate information is written into the registered water conservancy engineering drawing, specifically including: registering the water conservancy engineering drawing based on the second coordinate set; writing the registered water conservancy engineering drawing into a coordinate system consistent with the water body feature data; selecting two coordinates at random from the second coordinate set, and calculating coordinate information through distances between the selected two coordinates and preset pixels in the registered water conservancy engineering drawing, wherein the coordinate information specifically includes a horizontal coordinate of the preset pixel, an x-axis direction resolution of the preset pixel, a horizontal rotation coefficient, a vertical coordinate of the preset pixel, a y-axis direction resolution of the preset pixel, and a vertical rotation coefficient; writing the coordinate information into the registered water conservancy engineering drawing.

Images