An automatic line selection method based on GF-2 satellite image data analysis

Abstract

The present invention discloses an automatic line selection method based on GF-2 satellite image data analysis, comprising the steps of acquiring data, selecting line selection factors and assigning weights using the data; calculating an aggregated cost surface according to the weights; selecting a line selection scheme based on the aggregated cost surface; and generating a global optimal line selection scheme after linear optimization of the line selection scheme. The present invention optimizes the line selection scheme, improves work efficiency, reduces errors, and enables the line selection work to be completed in an automated manner.

Description

Technical Field

[0001] The present invention relates to the technical field of power system planning, and in particular to an automatic line selection method based on GF-2 satellite image data analysis. Background Art

[0002] In the design of modern power transmission networks, the planning of transmission lines is a crucial link, which has a significant impact on the laying cost of power lines, the flow and stability of the power system.

[0003] In the study of transmission line planning, early studies were limited by conditions and could not obtain accurate geographic information data. Therefore, the research basically believed that on a homogeneous map, the line selection was carried out with the lowest transmission line cost as the optimization goal and steady-state flow as the constraint. The main disadvantage of the traditional method is that it does not take geographical factors into consideration, the planning results are relatively rough, and a large number of manual and semi-automatic processes are required, including field control point measurement, indoor image interpretation and selection of control points, etc. The efficiency of obtaining control points is low and the cost is high, which cannot meet the needs of transmission line selection. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In view of the above existing problems, the present invention is proposed.

[0006] Therefore, the present invention provides an automatic line selection method based on GF-2 satellite image data analysis, which can avoid artificial errors and greatly improve work efficiency.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions: including, acquiring data, using the data to select and weight factors for line selection; calculating an aggregated cost surface according to the weights; selecting a line selection plan based on the aggregated cost surface; and generating a global optimal line selection plan after linear optimization of the line selection plan.

[0008] As a preferred solution of the automatic line selection method based on GF-2 satellite image data analysis described in the present invention, the data includes natural geographic data, human geographic data and power system data; the natural geographic data and the human geographic data are acquired by GF-2 images and geometric correction technology; the power system data is acquired by power grid equipment ledger or monitoring information.

[0009] As a preferred solution of the automatic line selection method based on GF-2 satellite image data analysis described in the present invention, the GF-2 image and geometric correction technology includes image positioning, control point acquisition and image registration.

[0010] As a preferred solution of the automatic line selection method based on GF-2 satellite image data analysis described in the present invention, the control point collection uses the minimum kernel value similarity area strategy.

[0011] As a preferred solution of the automatic line selection method based on GF-2 satellite image data analysis described in the present invention, the image registration uses a fast Fourier transform matching method to refer to the characteristic same-name points of the DOM image and the processed image.

[0012] As a preferred solution of the automatic line selection method based on GF-2 satellite image data analysis described in the present invention, wherein: the selection of line selection factors and the assignment of weights include selecting factors i that affect the line selection of transmission lines and assigning a value W to the degree of influence thereof i ; Assign R according to the degree to which the factor accepts or rejects the transmission line passing through i ; Wherein, i = 1, 2, ..., n; n is the total number of factors affecting the selection of transmission lines.

[0013] As a preferred solution of the automatic line selection method based on GF-2 satellite image data analysis described in the present invention, wherein: the calculation of the aggregation cost surface includes determining the aggregation cost of each pixel and connecting local minima, the aggregation cost of each pixel is determined using the Dijkstra algorithm, and the generated cost distance map is compiled into an aggregation cost surface; the connecting local minima is to connect the local minima with geometric constraints between the starting point and the end point, and the connection points are restricted by using the deflection angle between the azimuth and the end point and the minimum and maximum distance ranges.

[0014] As a preferred solution of the automatic line selection method based on GF-2 satellite image data analysis described in the present invention, the line selection solution based on the aggregated cost surface includes calculating the lowest cost point, length and degree of compliance of each edge with the target; determining the combined lowest cost path by connecting some of the lowest cost paths, and calculating the score of each connection; and selecting the path by comparing the scores.

[0015] As a preferred solution of the automatic line selection method based on GF-2 satellite image data analysis described in the present invention, the linear optimization includes linear optimization of all path alternatives, eliminating local optimal solutions until a global optimal line selection solution is generated.

[0016] The beneficial effects of the present invention are as follows: based on the analysis of the Gaofen-2 satellite image data, the line selection scheme is optimized, the work efficiency is improved, the error is reduced, and the line selection work can be completed in an automated manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0018] Figure 1 This is a flow chart of an automatic line selection method based on GF-2 satellite image data analysis according to the first embodiment of the present invention;

[0019] Figure 2 A schematic diagram of geometric decision rules for connecting nodes of an automatic line selection method based on GF-2 satellite image data analysis according to the first embodiment of the present invention;

[0020] Figure 3 A schematic diagram of an aggregated cost surface of an automatic line selection method based on GF-2 satellite image data analysis according to a second embodiment of the present invention;

[0021] Figure 4 A minimum cost path diagram of an automatic route selection method based on GF-2 satellite image data analysis according to the second embodiment of the present invention;

[0022] Figure 5 This is an alternative solution diagram of a lower cost center for an automatic line selection method based on GF-2 satellite image data analysis described in the second embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0024] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0025] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0026] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0027] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0028] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0029] Example 1

[0030] Reference Figures 1-2 , which is the first embodiment of the present invention, provides an automatic line selection method based on GF-2 satellite image data analysis, including:

[0031] S1: Obtain data and use the data to select and weight factors for line selection.

[0032] (1) Physical geographic data and human geographic data are obtained from GF-2 images and geometric correction technology; power system data are obtained from power grid equipment records or monitoring information.

[0033] (2) GF-2 image and geometric correction technology includes: image positioning, control point acquisition and image registration; among them, image positioning: using the first-order rational function model to read the image geometric information and build the model; control point acquisition: using the feature extraction algorithm to obtain the feature points of natural landscapes, buildings, etc. with prominent extreme points or characteristic patterns; image registration: overlapping the same-name images of multiple images through geometric transformation to achieve the unification of geographic coordinates and pixel spatial resolution between images.

[0034] ① The control point acquisition step uses the minimum kernel value similarity area method to sample the feature points of the processing image and the reference image respectively;

[0035] A nearly circular template (the central pixel of the template is called the kernel) is used to traverse the color image. By comparing the comprehensive scalar difference ΔV between each remaining pixel in the template and the central kernel pixel, a kernel value similarity area is used to define the number of points in the template that are the same or similar to the central kernel pixel. Finally, the size of the area is used to determine whether the central pixel of the template belongs to the edge.

[0036] Use the above-mentioned approximately circular template to scan the entire image, compare the size of each pixel in the template with the size of the central pixel comprehensive scalar V, and compare it with the given threshold value t to determine whether the pixel belongs to the minimum kernel value similarity area. The calculation formula is shown as follows:

[0037]

[0038] After comparing the threshold value, the number of pixels in the template that are similar to the central pixel value is used to judge the similarity between the pixels in the template and the central pixel value. The calculation formula for the minimum kernel value similar area size of each point in the image is as follows:

[0039]

[0040] Finally, by comparing the size of the minimum kernel value similarity area with the preset threshold g, we can determine whether it is an edge point: when the value of the minimum kernel value similarity area is less than or equal to g, the template center pixel is considered to be an edge point; when it is greater than g, the template center pixel is considered to be a non-edge point, as shown in the following formula:

[0041]

[0042] Among them, c(r,r0) is the discriminant function of whether the pixel in the template belongs to the minimum kernel value similarity area; V(r0) is the value of the central kernel pixel V of the template; V(r) is the V value of the remaining pixels in the template; t is the scalar difference threshold; D(r0) is the circular template area centered on r0, n(r0) is the size of the minimum kernel value similarity area of ​​each point in the image; R(r0) is the identifier of whether it is an edge point.

[0043] ② The image registration step uses the fast Fourier transform matching method to perform feature same-name point registration between the reference DOM image and the processed image.

[0044] When the fast Fourier transform matching method is used, when there is a relative drift between two images, the result is a phase difference in the frequency domain. The fast Fourier transform matching method can be applied to larger template sizes because it works in the frequency domain. It focuses on the details within the image rather than the grayscale values ​​in a small neighborhood. This makes the matching results of the fast Fourier transform matching method more stable when there are large brightness differences between the images or when large surface cover changes have occurred between the images. In addition, the fast Fourier transform matching method considers better matching between images from different sensors or the same area of ​​spectral bands.

[0045] Select the factors i that affect the selection of transmission lines and assign a value W to their influence degree i ; Assign R according to the degree to which the factor accepts or rejects the transmission line passing through i ; Wherein, i = 1, 2, ..., n; n is the total number of factors affecting the selection of transmission lines.

[0046] The mutual weight scoring of indicators is only for the corresponding conditions where all indicators are unit 1. The specific method is to compare the generalized investment when each geographical indicator is unit 1, and the ratio obtained is the mutual weight of the indicators, forming an indicator mutual weight matrix. The element in the i-th row and j-th column of the matrix represents the ratio of the generalized investment of the i-th geographical indicator unit 1 to the generalized investment of the j-th geographical indicator unit 1. The classification principles and scoring methods of each geographical indicator are detailed below:

[0047] Geographical indicators include the investigated natural geographical information and human geographical information, specifically, climate information, hydrological information, altitude information, altitude span information, landform information, land use information, transportation information and special zone information;

[0048] a). Climate information: no icing (1), slight icing, moderate icing, severe icing.

[0049] The broad investment measurement method used in this indicator is the probabilistic method, which calculates the sum of the product of the economic losses caused by the power outage due to the degree of icing and the probabilities of various degrees of power outages caused by this climate condition in the statistical data, that is, the expectation of the economic losses caused by the accident due to this degree of icing as the specific form of broad investment of this geographic direct indicator.

[0050] b) Hydrological information: water area accounts for 0% of the regional area (1), water area accounts for 0%-30% of the regional area, water area accounts for 30%-50% of the regional area, water area accounts for 50%-70% of the regional area, water area accounts for 70%-100% of the regional area

[0051] The generalized investment calculation method used in this information is the probability method, which uses the probability method to calculate the impact of different water area ratios on line length, and obtains the proportion of line length under each water condition relative to the case where the water area accounts for 0% of the grid area, as a score for various forms of various hydrological indicators.

[0052] c). Altitude information: 0-1000m (1), 1000-2000m, 2000-3000m, 3000-4000m, and above 4000m.

[0053] The broad investment estimation method used in this information is the expert scoring method. Experts are asked to make empirical estimates of the proportion of the cost of laying lines at various altitudes relative to low altitudes between 0-1000m, and use this estimate as a single indicator weight score between altitude information.

[0054] d). Altitude span information: Altitude span 0-100m(1), Altitude span 100-200m, Altitude span 200-300m, Altitude span 300-400m, Altitude span above 400m.

[0055] The broad investment estimation method used in this information is the expert scoring method. Experts are asked to make an empirical estimate of the ratio of the cost of laying lines between various altitude spans relative to the low altitude span of 0-100m, and use this estimate as a single indicator weight score between the altitude span information.

[0056] e). Topographic information: plains (1), hills, basins, plateaus, and mountains.

[0057] The broad investment estimation method used in this information is the expert scoring method. Experts are asked to make empirical estimates of the proportion of the cost of laying lines between various landforms relative to plain landforms, and use this estimate as a single indicator weight score between landform information.

[0058] f). Land use information: wasteland (1), cultivated land, and human activity areas.

[0059] The broad investment estimation method used in this information is the expert scoring method, in which experts are asked to make empirical estimates of the proportion of various land uses relative to the cost of laying lines between wastelands, and use this estimate as a single indicator weight score between land uses.

[0060] g). Traffic information: no traffic (1), light traffic, moderate traffic, developed traffic.

[0061] The broad investment measurement method used in this information is the expert scoring method. Experts are asked to make empirical estimates of the proportion of the cost of laying lines between various types of transportation information relative to those without transportation, and use this estimate as a single indicator weight score between transportation information.

[0062] h). Special area information: non-special areas (1), military areas, nature reserves.

[0063] The scoring method used in this information is the "all or nothing" method. For special areas such as military areas and nature reserves where transmission lines are not allowed to pass through, the value is assigned to infinity, and non-special areas are assigned to 1. After determining the scoring of each geographical form in each geographical indicator and the mutual indicator weight matrix, the eigenvector of the mutual indicator weight matrix is ​​obtained as the weight vector of the final score, which is called the final weight vector.

[0064] The assignment results are shown in the following table (× means it is forbidden to cross the area):

[0065] Table 1: Results of weight assignment of influencing factors.

[0066]

[0067]

[0068] The two assigned weights are corrected by the following formula:

[0069]

[0070] Next, the total resistance t at each point at location x is calculated using the linear utility function and multi-criteria decision analysis method by the following formula: x Perform the calculation:

[0071]

[0072] Among them, h i (R i ,W i ) is the corrected weight, W i is the degree to which the selected factors affect the selection of transmission lines, R i The degree to which the transmission line passes is accepted or rejected for the selected factor.

[0073] S2: Calculate the aggregate cost surface based on the weights.

[0074] Calculating the aggregate cost surface includes determining the aggregate cost of each pixel and connecting local minima. The aggregate cost of each pixel is determined using the Dijkstra algorithm. The resulting cost distance map is compiled into an aggregate cost surface, which represents the difficulty of reaching each point on the path from the starting point to the end point. The comprehensive cost surface can be interpreted as the ups and downs of low resistance and high resistance, from which it can be assumed that the path through low resistance represents a low-cost alternative to calculating the lowest cost point for each edge. However, even when considering the entire path length, these alternatives are not as good as calculating the lowest cost point for each edge in terms of total cost, but they can contain Pareto optimal sections with respect to one or more objectives. Therefore, a network of path alternatives passing through low resistance points is established, and these alternatives are evaluated according to the objectives listed in Table 1, allowing users to optimize the path array according to the interests of stakeholders.

[0075] Reference Figure 2 Connect Local Minima creates an undirected graph by connecting local minima with geometric constraints between the start and end points; the connection points are constrained by the azimuth and the deflection angle between the end points and the minimum and maximum distance ranges.

[0076] S3: Select a line selection scheme based on the aggregated cost surface.

[0077] Calculate the lowest cost point, length and degree of compliance of each edge to the target; determine the combined lowest cost path by connecting the partial lowest cost paths and calculate the score of each connection; select the path by comparing the scores.

[0078] It should be noted that the degree of compliance with the main objectives The range is 0 to 1 and is calculated by the following formula:

[0079]

[0080] Among them, len() is the function to determine the path length. is the area that the minimum cost path should not pass through, and LCP is the minimum cost path for each edge;

[0081] The combined minimum-cost path is determined by connecting the partial minimum-cost paths and calculating the score of each connection; path selection is performed by comparing the calculated scores, and what remains is a set of non-dominated path alternatives that represent the best trade-offs between multiple major objectives.

[0082] S4: Generate a global optimal line selection plan after linear optimization of the line selection plan.

[0083] All path alternatives are linearly optimized, and the local best solutions are eliminated until the global best route selection solution is generated;

[0084] Linear optimization of the solution that best suits the stakeholders is used to determine the solution that best suits the stakeholders; all path alternatives are linearly optimized, the local best solution is moved to the top of the sorted list and ignored in the next run, and finally the global best route selection solution is generated; the linear programming method uses expert answers to determine the degree of compliance with each goal Weight For each path j in a set of paths {1,…,k}, we obtain the weighted product Sum to calculate the value z j ; Decision variable d j Selected z j The largest path, which represents the best match between the primary objective and stakeholder preferences; the equation form of the linear optimization is:

[0085]

[0086] i∈{1,…,7}

[0087]

[0088]

[0089]

[0090]

[0091] Among them, Max z j To maximize the match between primary objectives and stakeholder preferences, For each goal compliance The weight of To the extent that the main objective is met, d j is the decision variable.

[0092] Preferably, the present embodiment realizes an automated line selection method through GF-2 satellite image data, a minimum kernel value similarity zone strategy, and a fast Fourier transform matching strategy, which not only improves efficiency but also obtains the most optimal line selection scheme.

[0093] Example 2

[0094] In order to verify and illustrate the technical effect adopted in this method, this embodiment adopts this method to carry out simulation experiment, and uses the experimental results by means of scientific demonstration to verify the real effect of this method.

[0095] In order to verify that this method can improve the efficiency of line selection, this embodiment uses this method to evaluate the importance of seven main objectives (Ω1-Ω7) based on the experience of transmission line planning, as shown in the following table;

[0096] Table 2: Importance assessment table of the seven main objectives (Ω1-Ω7).

[0097]

[0098]

[0099] Among them, P i For participants, C p For each participant, the corresponding organizational category,Ω i Indicates the degree to which participants consider the corresponding main goal important; through clustering, relevant groups are obtained. p .

[0100] This method displays the planning area, path alternatives, complete minimum cost paths and layers in a geographic information map by calculating an aggregated cost surface using weights, selecting non-dominated options based on the aggregated cost surface, and performing linear optimization on the solution that best suits the stakeholders.

[0101] Reference for pre-planning map based on Gaofen-2 satellite image data Figure 3 As shown, first the weight calculation is performed, then the aggregation cost of each pixel is determined, and the generated cost distance map is compiled into an aggregation cost surface, which represents the difficulty of reaching each point on the path from the starting point to the end point; the depth of black and white colors is used to represent the resistance, that is, the degree of difficulty; the lighter the color, the greater the resistance, and the darker the color, the smaller the resistance.

[0102] Connecting local minima is to connect the local minima with geometric constraints between the starting point and the end point, and restrict the connection points accordingly according to the deflection angle between the azimuth and the end point and the minimum and maximum distance ranges to represent them as the low aggregation cost surface of the planning center. Figure 4 As shown; the bold dotted line is the lowest cost path in the planning area.

[0103] The non-dominated solution selection based on the aggregate cost surface is to calculate the lowest cost point, length and degree of compliance of each edge with the main goal; then, by connecting the partial lowest cost paths to determine the combined lowest cost path, the alternative with a lower cost center can be obtained. Figure 5 shown.

[0104] It should be appreciated that embodiments of the present invention may be implemented or enforced by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer-readable memory. The method may be implemented in a computer program using standard programming techniques - including a non-transitory computer-readable storage medium configured with a computer program, wherein the storage medium so configured causes the computer to operate in a specific and predefined manner - according to the methods and drawings described in the specific embodiments. Each program may be implemented in a high-level procedural or object-oriented programming language to communicate with a computer system. However, if desired, the program may be implemented in an assembly or machine language. In any case, the language may be a compiled or interpreted language. In addition, the program may be run on a programmed ASIC for this purpose.

[0105] Furthermore, the operations of the processes described herein may be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The processes described herein (or variations and / or combinations thereof) may be performed under the control of one or more computer systems configured with executable instructions, and may be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) that is executed collectively on one or more processors, by hardware, or a combination thereof. The computer program includes a plurality of instructions that may be executed by one or more processors.

[0106] Further, the method can be implemented in any type of computing platform that is operably connected to a suitable computer, including but not limited to a personal computer, a minicomputer, a mainframe, a workstation, a network or distributed computing environment, a separate or integrated computer platform, or in communication with a charged particle tool or other imaging device, etc. Aspects of the present invention can be implemented in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, an optical read and / or write storage medium, a RAM, a ROM, etc., so that it can be read by a programmable computer, and when the storage medium or device is read by the computer, it can be used to configure and operate the computer to perform the process described herein. In addition, the machine-readable code, or part thereof, can be transmitted via a wired or wireless network. When such media includes instructions or programs that implement the steps described above in conjunction with a microprocessor or other data processor, the invention described herein includes these and other different types of non-transitory computer-readable storage media. When programmed according to the methods and techniques described in the present invention, the present invention also includes the computer itself. The computer program can be applied to input data to perform the functions described herein, thereby converting the input data to generate output data stored in a non-volatile memory. The output information can also be applied to one or more output devices such as a display. In a preferred embodiment of the present invention, the converted data represents a physical and tangible object, including a specific visual depiction of the physical and tangible object produced on a display.

[0107] As used in this application, the terms "component", "module", "system", etc. are intended to refer to a computer-related entity, which can be hardware, firmware, a combination of hardware and software, software, or software in operation. For example, a component can be, but is not limited to: a process running on a processor, a processor, an object, an executable file, a thread in execution, a program, and / or a computer. As an example, an application running on a computing device and the computing device can both be components. One or more components can exist in a process and / or thread in execution, and a component can be located in a computer and / or distributed between two or more computers. In addition, these components can be executed from various computer-readable media having various data structures thereon. These components can communicate in a local and / or remote process manner, such as according to a signal having one or more data packets (e.g., data from a component that interacts with another component in a local system, a distributed system, and / or interacts with other systems in a signal manner through a network such as the Internet).

[0108] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An automatic line selection method based on GF-2 satellite image data analysis, characterized in that: include, Acquire data, and use the data to select and weight factors for line selection; The data include natural geographic data, human geographic data and power system data; wherein the natural geographic data and the human geographic data are acquired by GF-2 images and geometric correction technology; the power system data are acquired by power grid equipment records or monitoring information; The GF-2 image and geometric correction technology includes image positioning, control point acquisition and image registration; The control point collection uses the minimum kernel value similarity area strategy; The selection of factors for line selection and the assignment of weights include: Select the factors i that affect the selection of transmission lines and assign a value W to their influence degree i ; Assign a value R based on the degree to which the factor accepts or rejects the transmission line passing through i ; Wherein, i = 1, 2, ..., n; n is the total number of factors affecting the selection of transmission lines; The two assigned weights are corrected by the following formula: Calculate the aggregated cost surface after weight correction; The computing of the aggregation cost surface includes determining the aggregation cost of each pixel and connecting local minima. The aggregation cost of each pixel is determined by using the Dijkstra algorithm, and the generated cost distance map is compiled into an aggregation cost surface; The connecting local minimum value is to connect the local minimum values ​​with geometric constraints between the starting point and the end point, and limit the connection point by using the deflection angle between the azimuth and the end point and the minimum and maximum distance ranges; Select the route selection scheme based on the aggregated cost surface; Producing a global optimal line selection scheme after linear optimization of the line selection scheme; The linear optimization includes performing linear optimization on all the alternative path solutions, eliminating the local best solution until a global best line selection solution is generated; The linear programming method uses the expert answers to determine the degree to which each goal is met Weight For each path j in a set of paths {1,…,k}, we obtain the weighted product Sum to calculate the value z j ; Decision variable d j Selected z j The largest path, which represents the best match between the primary goal and stakeholder preferences.

2. The automatic line selection method based on GF-2 satellite image data analysis according to claim 1, characterized in that: The image registration uses a fast Fourier transform matching method to reference the characteristic same-name points of the DOM image and the processed image.

3. The automatic line selection method based on GF-2 satellite image data analysis according to claim 1, characterized in that: The line selection scheme based on the aggregated cost surface includes: Calculate the lowest cost point, length and degree of compliance of each edge with the goal; Determine the combined minimum cost path by connecting the partial minimum cost paths and calculate the score of each connection; Path selection is performed by comparing the scores.

Images