Image terminal preset bit detection evaluation method and system

Abstract

The application relates to an image terminal preset position detection evaluation method and system. The method comprises the following steps: acquiring a plurality of preset position layout schemes; acquiring a plurality of criteria for evaluating the preset position layout schemes; acquiring indexes corresponding to each criterion according to the preset position layout schemes; combining subjective and objective weights of the indexes by using an analytic hierarchy process and an entropy weight method; and evaluating the preset position layout schemes according to the weighted indexes. The method can evaluate the preset position layout schemes at a low cost, thereby guaranteeing the image shooting quality during power inspection.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image acquisition, in particular to an image terminal preset position detection evaluation method and system. BACKGROUND

[0002] The inspection and maintenance work of power equipment in a substation is an important part of ensuring the safe and stable operation of the power system. At present, the intelligent and digital transformation of the power industry in China is being fully promoted, and the intelligent construction of substations is an important part of it. Intelligent image terminals represented by robots and drones are gradually replacing manual work as the main tool for power equipment inspection. The main work content is that the intelligent image terminal carries an imaging sensor to take inspection images of the target to be inspected at the preset position in the station. The intelligent system and technical workers judge the operating conditions of each power equipment in the substation through these image data, and replace the equipment that may have defects or faults in time to avoid serious accidents.

[0003] However, the preset position layout of the image terminal is still evaluated according to manual experience, resulting in high evaluation cost and difficulty in ensuring the shooting quality of the laid image terminal. SUMMARY

[0004] Therefore, it is necessary to provide a low-cost image terminal preset position detection evaluation method and system that can ensure the image shooting quality during power inspection.

[0005] In a first aspect, the present application provides an image terminal preset position detection evaluation method. The method comprises:

[0006] Obtaining a plurality of preset position layout schemes;

[0007] Obtaining a plurality of criteria for evaluating the preset position layout schemes;

[0008] According to the preset position layout scheme, obtaining the index corresponding to each criterion;

[0009] Combining the index by using the analytic hierarchy process and the entropy weight method, and evaluating the preset position layout scheme according to the weighted index.

[0010] In one of the embodiments, the criteria include image quality criteria, light matching criteria, and inspection efficiency criteria.

[0011] In one of the embodiments, the image quality criteria corresponding index includes target occlusion rate, target average size, and average shooting angle;

[0012] The light matching criteria corresponding index includes backlight shooting rate and average light angle;

[0013] The patrol efficiency criteria correspond to indexes including task completion rate, preset point number, task time consumption and unit target time consumption.

[0014] In one of the embodiments, the obtaining of the plurality of preset point layout schemes comprises:

[0015] A normalized matrix of the shooting potential of the space is established, and elements in the normalized matrix are the shooting potential corresponding to the space points;

[0016] The shooting potential is compared with a threshold value, and the space points are preliminarily screened according to the comparison result;

[0017] A single space constraint is established, and a target function for solving the maximum of the total shooting potential is established based on the single space constraint;

[0018] The target function is refined screened according to the ant colony algorithm, and a target solution of the target function is obtained;

[0019] The preset points are selected from the space points and the preset point layout scheme is obtained according to the target solution.

[0020] In one of the embodiments, the subjective and objective combined weighting of the indexes is performed by using the analytic hierarchy process and the entropy weight method, and the preset point layout scheme evaluation is performed according to the weighted indexes, which comprises:

[0021] The subjective weight is determined according to the analytic hierarchy process;

[0022] The objective weight is determined according to the entropy weight method;

[0023] The comprehensive weight is determined according to the subjective weight and the objective weight;

[0024] For each preset point layout scheme, the indexes are weighted according to the comprehensive weight, and an evaluation index is obtained;

[0025] The target layout scheme is selected from the plurality of preset point layout schemes according to the evaluation index.

[0026] In one of the embodiments, the comprehensive weight is determined according to the subjective weight and the objective weight, which comprises:

[0027] The intermediate value corresponding to the index is obtained according to the arithmetic square root of the product of the subjective weight and the objective weight corresponding to the same index;

[0028] The comprehensive weight of the index corresponding to the intermediate value as the numerator is obtained with the sum of the intermediate values corresponding to the indexes as the denominator.

[0029] In a second aspect, the application provides an image terminal preset point detection and evaluation system, characterized in that the system comprises:

[0030] A target layer is configured to obtain a plurality of preset point layout schemes;

[0031] A criterion layer is configured to acquire a plurality of criteria for evaluating the preset position layout scheme;

[0032] An index layer is configured to acquire indexes corresponding to each criterion according to the preset position layout scheme;

[0033] A scheme layer is configured to combine subjective and objective weights of the indexes by using the analytic hierarchy process and the entropy weight method, and evaluate the preset position layout scheme according to the weighted indexes.

[0034] In a third aspect, the present application provides a computer device, comprising a memory and a processor, and the memory stores a computer program, characterized in that the processor implements the following steps when executing the computer program:

[0035] acquiring a plurality of preset position layout schemes;

[0036] acquiring a plurality of criteria for evaluating the preset position layout scheme;

[0037] acquiring indexes corresponding to each criterion according to the preset position layout scheme;

[0038] combining subjective and objective weights of the indexes by using the analytic hierarchy process and the entropy weight method, and evaluating the preset position layout scheme according to the weighted indexes.

[0039] In a fourth aspect, the present application provides a computer readable storage medium, which stores a computer program, characterized in that the computer program is executed by a processor to implement the following steps:

[0040] acquiring a plurality of preset position layout schemes;

[0041] acquiring a plurality of criteria for evaluating the preset position layout scheme;

[0042] acquiring indexes corresponding to each criterion according to the preset position layout scheme;

[0043] combining subjective and objective weights of the indexes by using the analytic hierarchy process and the entropy weight method, and evaluating the preset position layout scheme according to the weighted indexes.

[0044] In a fifth aspect, the present application provides a computer program product, comprising a computer program, characterized in that the computer program is executed by a processor to implement the following steps:

[0045] acquiring a plurality of preset position layout schemes;

[0046] acquiring a plurality of criteria for evaluating the preset position layout scheme;

[0047] acquiring indexes corresponding to each criterion according to the preset position layout scheme;

[0048] The index is combined with subjective and objective weights by using analytic hierarchy process and entropy weight method, and the preset position layout scheme is evaluated according to the weighted index.

[0049] The image terminal preset position detection evaluation method and system, by establishing the preset position layout scheme evaluation system composed of multiple criteria and multiple indexes, and using analytic hierarchy process and entropy weight method to determine the comprehensive weight of the index, realizes the selection of the joint preset position layout scheme with the maximum closeness from multiple candidate schemes as the optimal scheme. After the evaluation system is established, the dependence on manual analysis is greatly reduced, and when the power equipment changes in time and space and adjusts the preset position, the evaluation system is also applicable, and has strong flexibility. BRIEF DESCRIPTION OF DRAWINGS

[0050] Figure 1 It is an application environment diagram of the image terminal preset position detection evaluation method in an embodiment;

[0051] Figure 2 It is a flowchart of the image terminal preset position detection evaluation method in an embodiment;

[0052] Figure 3 It is a flowchart of obtaining a plurality of preset position layout schemes in an embodiment;

[0053] Figure 4 It is a structure block diagram of the image terminal preset position detection evaluation system in an embodiment;

[0054] Figure 5 It is an internal structure diagram of the computer device in an embodiment. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical scheme and advantages of the present application clearer, the present application will be further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not to limit the present application.

[0056] The image terminal preset position detection evaluation method provided by the embodiment of the present application can be applied in the application environment as shown in the figure. Figure 1 The terminal 102 communicates with the server 104 through the network. The data storage system can store the data required to be processed by the server 104. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers. The terminal 102 can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, unmanned aerial vehicles, inspection robots. The server 104 can be realized by an independent server or a server cluster composed of multiple servers.

[0057] The intelligent image terminal shoots the inspection image of the target to be inspected at the preset position by carrying the imaging sensor, so as to assist in judging the state of the power equipment. The layout of the preset position directly affects the image quality obtained by the intelligent image terminal. According to the statistics of State Grid, under the premise of accurate positioning, more than 80% of the total operation failures of the inspection robot are caused by unreasonable inspection shooting points, which mainly because the image terminal preset position of the intelligent image terminal is currently preset and evaluated by artificial experience, and lacks guiding layout criteria and indicators, so that the layout of the image terminal preset position is difficult to guarantee the shooting quality. At the same time, due to the high cost and large amount of manual layout, it is impossible to adjust the point at any time with the change of time and space conditions, resulting in poor adaptability and robustness of the manually laid image terminal preset position, and the shooting quality cannot be guaranteed, which is difficult to meet the actual intelligent inspection demand.

[0058] The current research on the automatic generation of high-quality image terminal preset positions of intelligent image terminals in substations has the following difficulties: first, the image terminal preset position of the intelligent image terminal is set to obtain high-quality inspection images, but the evaluation of image quality is usually qualitative rather than quantitative, which makes it difficult to evaluate the quality of the image terminal preset position. Second, there are many types and large quantities of power equipment in substations, and there are complex electrical connections between equipment, which makes the spatial relationship between the intelligent image terminal and the equipment very complex, resulting in high computational complexity and great difficulty in solving. Finally, due to the different constraint conditions of different intelligent image terminals, and the need to consider low energy consumption and high shooting quality in setting the image terminal preset position and shooting scheme, which increases the complexity of solving the joint inspection problem.

[0059] Therefore, the existing evaluation index and evaluation method cannot objectively and comprehensively quantitatively evaluate the intelligent terminal preset position, and a new evaluation system needs to be established to evaluate the performance of the image terminal preset position.

[0060] In one embodiment, as shown in Figure 2 , an image terminal preset position detection and evaluation method is provided, which is applied to the terminal 102 in Figure 1 for example, including the following steps:

[0061] Step 202, obtaining a plurality of preset position layout schemes.

[0062] Among them, the preset position layout scheme can be laid by artificial method, or can be realized by algorithm; the starting point of the layout can be machine cost, shooting quality, detail shooting, etc.

[0063] Step 204, obtaining a plurality of criteria for evaluating the preset position layout scheme.

[0064] The criteria for evaluating the preset position layout scheme include image quality obtained by the intelligent image terminal during inspection, adaptability of the intelligent image terminal to changing space-time conditions (mainly embodied as the degree of fitting with sunlight), and execution efficiency of the inspection work, etc.

[0065] In step 206, indexes corresponding to each criterion are obtained according to the preset position layout scheme.

[0066] Each criterion defines a general direction for evaluating the preset position layout scheme, and the indexes give specific quantifiable values on the basis of the criteria, so that the preset position layout scheme can be quantitatively analyzed by the values, thereby obtaining a more reliable evaluation result.

[0067] In step 208, the indexes are combined and weighted by subjective and objective methods by using the analytic hierarchy process and the entropy weight method, and the preset position layout scheme is evaluated according to the weighted indexes.

[0068] The weights of the indexes are determined by the analytic hierarchy process and the entropy weight method, so that the subjective and objective methods are combined to reflect the influence of each index on the evaluation of the preset position layout scheme.

[0069] In the above image terminal preset position detection and evaluation method, the preset position layout scheme evaluation system is established by multiple criteria and multiple indexes, and the comprehensive weights of the indexes are determined by using the analytic hierarchy process and the entropy weight method, so that the joint preset position layout scheme with the closest degree is selected from multiple candidate schemes as the optimal scheme. After the evaluation system is established, the dependence on manual analysis is greatly reduced, and the evaluation system is also applicable when the preset position is adjusted due to the space-time changes of the power equipment, so that the evaluation system has strong flexibility.

[0070] In one embodiment, the criteria include an image quality criterion, a light fitting criterion, and an inspection efficiency criterion.

[0071] In one embodiment, the indexes corresponding to the image quality criterion include a target occlusion rate, a target average size, and an average shooting angle; the indexes corresponding to the light fitting criterion include a backlight shooting rate and an average light angle; and the indexes corresponding to the inspection efficiency criterion include a task completion rate, a preset point number, a task time consumption, and a unit target time consumption.

[0072] In one embodiment, as shown in FIG. 2B, step 202 includes: Figure 3

[0073] In step 302, a space shooting potential normalization matrix is established, and the elements in the normalization matrix are the shooting potentials corresponding to the space points.

[0074] ​The factors affecting the shooting effect of the preset position of the intelligent image terminal in the substation include three aspects, namely, the spatial relationship between the preset position and the equipment, the adaptability of the preset position to the environment, and the efficiency of the intelligent image terminal in executing the preset position. The embodiment comprehensively considers the three factors, proposes a shooting potential model similar to electric potential, and the following formula gives the calculation method of the shooting potential U of the intelligent image terminal in shooting the target S to be inspected at the coordinate P(x, y, z) PS

[0075]

[0076] Wherein, S is the area of the target to be inspected, p s is the area information density, which represents the importance of S, s s (x, y, z) is the area integral element. The smaller the angle between the line of sight of the preset position camera and the normal vector of the surface, the more positive the shooting angle, and the smaller the deformation of the target in the picture. When S is observed at P to be blocked by other equipment, U PS is 0.

[0077] When considering the environmental light, let the angle between the line of sight and the light vector be Then the shooting potential needs to be multiplied by a light influence coefficient k, and the calculation method of the shooting potential U' is PS

[0078]

[0079] Wherein,

[0080] The shooting potential can be used to calculate the pros and cons of the spatial relationship between the preset position and the equipment, including the distance between the preset position and the equipment, the inclination angle of the preset position to the equipment, and the degree of blocking by other equipment when the preset position observes the target equipment. The shooting potential also considers the degree of fit with the environmental light.

[0081] In the embodiment, for each target to be inspected, there are several spatial points that can be used to inspect and shoot the target without being blocked, otherwise the target to be inspected should be monitored and evaluated by other detection means.

[0082] The shooting potential of the target to be inspected is calculated for several preset positions, and the shooting potentials are presented in the form of a normalized matrix.

[0083] In step 304, the shooting potential is compared with the threshold value, and the spatial points are preliminarily screened according to the comparison result.

[0084] According to the calculation result of the shooting potential, the spatial points with higher shooting potential are more suitable for shooting the target to be inspected. After normalizing the shooting potential of these spatial points, the points with a potential value lower than a certain threshold value are removed, and the remaining points are taken as candidate points and entered into a candidate point set. ​​

[0085] Step 306, a single space constraint is established, and a target function of sum of normalized shooting potential maximum is established based on the single space constraint.

[0086] For a single kind of intelligent image terminal, the action space is subject to certain constraints, such as the unmanned aerial vehicle must maintain a safe distance from the substation equipment and cannot cross the equipment; the robot can only move on the planned road. These constraints on the action space are realized through a single space constraint.

[0087] Step 308, the target function is refined according to the ant colony algorithm to obtain a target solution of the target function.

[0088] The ant colony algorithm takes the maximum of the normalized sum of shooting potential of the preset position as the optimization target, which can ensure the shooting quality while selecting the preset positions that can inspect more targets at a point to improve the inspection efficiency, and finally selects the optimal set covering the inspection task as the preset position set to complete the automatic deployment of the intelligent image terminal preset position.

[0089] Step 310, selecting a preset position from the space points according to the target solution and obtaining a preset position deployment scheme.

[0090] The space points in step 310 are the space points filtered in step 304. The preset position with the maximum normalized sum of shooting potential that satisfies the space constraint is obtained through the target solution set, and then the preset position deployment scheme can be obtained.

[0091] In one embodiment, step 208 includes: determining a subjective weight according to the analytic hierarchy process; determining an objective weight according to the entropy weight method; determining a comprehensive weight according to the subjective weight and the objective weight; for each preset position deployment scheme, weighting the indicators according to the comprehensive weight to obtain an evaluation index; and selecting a target deployment scheme from the several preset position deployment schemes according to the evaluation index.

[0092] The analytic hierarchy process is mainly used to determine the importance of lower information to upper information, so as to determine the importance of the indicators themselves to the target decision. The steps of determining the subjective weight of the indicators by the analytic hierarchy process according to the solved standard decision matrix are as follows:

[0093] Construct a judgment matrix B layer by layer, and suppose that there are n indicators in the lower layer of a certain layer, then:

[0094]

[0095] wherein b ij =1 / b ji (i,j=1,2,…,n), the value is given by the judgment matrix scale table, and table 1 gives the scale and meaning of the judgment matrix.

[0096] Table 1 Judgment Matrix Scale Table

[0097]

[0098] The maximum eigenvalue and eigenvector of the judgment matrix are calculated, and consistency check is performed, and the weight is the normalized eigenvector.

[0099] The calculation method of the consistency judgment index CI is:

[0100]

[0101] Where λ max is the maximum eigenvalue of the matrix, and n is the dimension of the current judgment matrix. The consistency check method is:

[0102]

[0103] When CR<0.1, it is considered that the judgment matrix meets the consistency check, that is, the subjective importance given is reasonable compared with the whole. In the formula, RI is the average random consistency index, and according to the table, when n=2, no consistency check is needed, when n=3, RI=0.58, and when n=4, RI=0.89.

[0104] When the consistency check is met, the weight is the normalized eigenvector, otherwise the judgment matrix needs to be adjusted. The weight of the index layer to the target layer can be obtained by multiplying the weight of the criterion layer to the target layer and the weight of the index layer to the criterion layer. j (j=1,2,...,n).

[0105] The core idea of the entropy weight method is to judge the dispersion degree of a certain index by calculating the information entropy, and then to judge the importance of the index in the index system. Generally speaking, the smaller the information entropy value of the index, the greater the dispersion degree of the index, and the greater the influence weight of the index on the index system. The steps of determining the weight by the entropy weight method combined with the content of the present application are as follows:

[0106] A decision matrix of evaluation indexes is constructed. Assuming that there are m candidate schemes (i=1, 2,..., m) and n evaluation indexes (j=1, 2,..., n), the initial decision matrix X is:

[0107]

[0108] Different indexes have different data dimensions and inconsistent orientations, and there are positive indexes and reverse indexes in the indexes, so the decision matrix needs to be normalized and standardized. Since the reverse indexes in the evaluation system are minimum data, the reverse indexes are processed as follows:

[0109]

[0110] The initial decision matrix X is converted into a positive matrix Y by the above formula.

[0111] To eliminate the influence of different dimensions, the Y is normalized to obtain a standard decision matrix Z, and for the matrix Z, there is:

[0112]

[0113] The contribution degree p of the i-th (i = 1, 2,..., m) scheme to the j-th (j = 1, 2,..., n) index is solved by using the standard decision matrix Z. ij :

[0114]

[0115] The information entropy E of the index j is solved. j :

[0116]

[0117] The attribute importance D of each index is solved. j and the objective weight β j :

[0118]

[0119] The comprehensive weight can be obtained by using α j and β j .

[0120] In one embodiment, determining the comprehensive weight according to the subjective weight and the objective weight comprises: obtaining an intermediate value corresponding to an index according to the arithmetic square root of the product of the subjective weight and the objective weight corresponding to the same index; and obtaining the comprehensive weight of the index corresponding to the intermediate value as the numerator and the sum of the intermediate values corresponding to each index as the denominator.

[0121] The comprehensive weight of the index is determined by the following formula in this embodiment:

[0122]

[0123] In the formula, α j and β j are the subjective weight and the objective weight of the index j determined by the analytic hierarchy process and the entropy weight method, and w j is the comprehensive weight of the index j.

[0124] The application studies the problem of realizing intelligent inspection in a substation by an intelligent image terminal, and proposes an image terminal preset position detection and evaluation method. Then, an evaluation index system of the preset position is established, which includes evaluation indexes of shooting quality, light matching degree and efficiency of the preset position. The improved TOPSIS method determines the comprehensive weights of the indexes by the analytic hierarchy process and entropy weight method, and finally selects the joint preset position layout scheme with the largest closeness degree from multiple candidate schemes as the optimal scheme. The algorithm of the application is verified in a virtual substation experimental platform, and the results show that the proposed method can flexibly, quickly and automatically generate high-quality preset positions suitable for intelligent image terminals. Compared with other methods, the proposed joint inspection strategy of multiple intelligent image terminals can obviously improve the shooting quality and inspection efficiency, and the selection results are verified by the actual shooting images.

[0125] To verify the feasibility of the preset position layout scheme optimization method of the intelligent image terminal in the substation, an example calculation is performed on a 110kV substation in China. The substation scene is 110 meters long, 120 meters wide and 50 meters high. The inspection task includes 467 device components and 220 to-be-inspected surfaces. The auxiliary verification experiment is performed on the 1:1 digital handover scene model of the substation built in the UE4 platform, the preset positions laid by the candidate schemes are tested, and the visible light images of the targets are simulated under the camera parameters in the real scene.

[0126] The basic situations of the five candidate schemes are shown in Table 2.

[0127] Table 2 Index data of candidate schemes

[0128]

[0129] According to the data in Table 2, the initial decision matrix X and the standard decision matrix Z are obtained, wherein

[0130]

[0131] After the forward and normalization of X according to the corresponding formula, the standard decision matrix Z is obtained,

[0132]

[0133] The comprehensive weight w of the index is determined j . First, the subjective weight of the 9 indexes in the index layer to the target layer preset position layout scheme is determined by the analytic hierarchy process j (j=1, 2,..., 9).

[0134] Table 3 gives the judgment matrix and weight of the criterion layer to the target layer, and Tables 4 to 6 give the judgment matrix and weight of the index layer to the criterion layer. The elements of the judgment matrix are determined by relevant experts after discussion.

[0135] Table 3 Judgment matrix and weight of criteria layer to target layer T

[0136]

[0137] According to Table 3, the maximum eigenvalue λ max is 3.0092, and the CR value is 0.008.

[0138] Table 4 Judgment matrix and weight of index layer to criteria layer B1

[0139]

[0140] According to Table 4, the maximum eigenvalue λ max is 3.0092, and the CR value is 0.008.

[0141] Table 5 Judgment matrix and weight of index layer to criteria layer B2

[0142]

[0143] According to Table 5, the maximum eigenvalue λ max is 2, and the CR value is 0.

[0144] Table 6 Judgment matrix and weight of index layer to criteria layer B3

[0145]

[0146]

[0147] According to Table 6, the maximum eigenvalue λ max is 4.0145, and the CR value is 0.049.

[0148] According to the analytic hierarchy process, the subjective weight α of the index layer to the target layer is obtained.

[0149] α = [0.2911, 0.0882, 0.1603, 0.0743, 0.2228, 0.0789, 0.0144, 0.0256, 0.0444]

[0150] According to the calculation formula of the entropy weight method, the objective weight β of each index is obtained as

[0151] β = [0.0015, 0.1382, 0.0119, 0.4800, 0.0497, 0.0068, 0.2712, 0.0221, 0.0186]

[0152] The comprehensive weight w is obtained by the comprehensive weight calculation formula as

[0153] w = [0.1835, 0.0744, 0.1769, 0.0871, 0.1535, 0.1896, 0.4206, 0.2450, 0.2326]

[0154] The indicators in each scheme are weighted and summed by using the comprehensive weight, and finally the optimal preset bit layout scheme is selected, and the optimal intelligent image terminal preset bit layout scheme of the substation is selected according to the closeness degree.

[0155] It should be understood that, although each step in the flowchart involved in each embodiment as described above is displayed in sequence according to the arrow, these steps are not necessarily executed in sequence according to the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other sequences. Moreover, at least part of the steps in the flowchart involved in each embodiment as described above can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least part of other steps or steps or stages in other steps.

[0156] Based on the same inventive concept, the embodiment of the present application also provides an image terminal preset bit detection and evaluation system for implementing the above-mentioned image terminal preset bit detection and evaluation method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more image terminal preset bit detection and evaluation system embodiments provided below can refer to the limitations of the image terminal preset bit detection and evaluation method in the above text, and will not be repeated here.

[0157] In one embodiment, as shown in Figure 4 An image terminal preset bit detection and evaluation system is provided, comprising: a target layer 402, a criterion layer 404, an index layer 406, and a scheme layer 408, wherein:

[0158] The target layer 402 is configured to obtain a plurality of preset bit layout schemes.

[0159] The criterion layer 404 is configured to obtain a plurality of criteria for evaluating the preset bit layout schemes.

[0160] The index layer 406 is configured to obtain indicators corresponding to each criterion according to the preset bit layout schemes.

[0161] The scheme layer 408 is configured to combine subjective and objective weights of the indicators by using the analytic hierarchy process and the entropy weight method, and evaluate the preset bit layout schemes according to the weighted indicators.

[0162] The criteria include an image quality criterion, an illumination fitting criterion, and an inspection efficiency criterion.

[0163] The image quality criterion corresponds to indexes including a target occlusion rate, a target average size, and an average shooting angle; the illumination fitting criterion corresponds to indexes including a backlight shooting rate and an average illumination angle; and the inspection efficiency criterion corresponds to indexes including a task completion rate, a preset point number, a task time consumption, and a unit target time consumption.

[0164] The target layer 402 is further configured to establish a normalized matrix of spatial shooting potential, elements in the normalized matrix are shooting potentials corresponding to spatial points, perform a preliminary screening on the spatial points according to a comparison result of the shooting potentials and a threshold, establish a single spatial constraint, establish a target function for solving a maximum shooting potential sum based on the single spatial constraint, perform a fine screening on the target function according to an ant colony algorithm to obtain a target solution of the target function, and select a preset position from the spatial points and obtain a preset position layout scheme according to the target solution.

[0165] The scheme layer 408 is further configured to determine a subjective weight according to an analytic hierarchy process, determine an objective weight according to an entropy weight method, determine a comprehensive weight according to the subjective weight and the objective weight, for each preset position layout scheme, weight indexes according to the comprehensive weight to obtain an evaluation index, and select a target layout scheme from the several preset position layout schemes according to the evaluation index.

[0166] The scheme layer 408 is further configured to obtain an intermediate value corresponding to an index according to an arithmetic square root of a product of a subjective weight and an objective weight corresponding to the same index, and obtain a comprehensive weight of the index corresponding to the intermediate value as a numerator and a sum of intermediate values corresponding to all indexes as a denominator.

[0167] The above-mentioned modules in the image terminal preset position detection and evaluation system can be realized by software, hardware, or a combination thereof. The above-mentioned modules can be embedded in or independent of a processor in a computer device in a hardware form, or can be stored in a memory in a computer device in a software form, so as to be called and executed by a processor to perform operations corresponding to the above-mentioned modules.

[0168] In one embodiment, a computer device is provided, which can be a server, and an internal structure diagram of the computer device can be as shown in FIG. 8. Figure 5As shown in the figure. The computer device includes a processor, a memory, an input / output interface (I / O for short) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through the system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capability. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store power equipment related image data. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through network connection. The computer program is executed by the processor to realize an image terminal preset bit detection evaluation method.

[0169] In one embodiment, a computer device is provided, which can be a terminal, and its internal structure diagram can be as shown in the figure. Figure 5 As shown in the figure. The computer device includes a processor, a memory, an input / output interface (I / O for short) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through the system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capability. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store power equipment related image data. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through network connection. The computer program is executed by the processor to realize an image terminal preset bit detection evaluation method.

[0170] Those skilled in the art can understand that, Figure 5 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0171] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to realize all the method embodiments described above.

[0172] In an embodiment, a computer readable storage medium is provided, having stored thereon a computer program which, when executed by a processor, implements all the method embodiments described above.

[0173] In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements all the method embodiments described above.

[0174] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0175] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric memory (Ferroelectric Random Access Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0176] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0177] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. An image terminal preset position detection evaluation method characterized by comprising: The method comprises: The method comprises the following steps: obtaining a plurality of preset position layout schemes, establishing a space shooting potential normalization matrix, the elements in the normalization matrix are corresponding shooting potentials of space points, comparing the shooting potentials with a threshold value, and performing a preliminary screening on the space points according to the comparison result; establishing a single space constraint, establishing a target function for solving the maximum sum of the shooting potentials based on the single space constraint; performing a fine screening on the target function according to an ant colony algorithm, obtaining a target solution of the target function; selecting the preset positions from the space points according to the target solution and obtaining the preset position layout scheme; and calculating the shooting potential of a to-be-inspected target at a space point P (x p , y p , z p ) according to the following formula: Wherein, S is the area of the region where the target to be inspected is located, p s is the surface information density, to represent the importance of S, σ s is the area element, and θ is the angle between the preset camera line of sight and the surface normal vector. The smaller the angle is, the more normal the shooting angle is, and the smaller the deformation of the target to be inspected in the picture is. acquiring a plurality of criteria for evaluating the preset position layout scheme; acquiring an index corresponding to each of the criteria according to the preset position layout scheme; combining subjective and objective weights of the index by using the analytic hierarchy process and the entropy weight method, and evaluating the preset position layout scheme according to the weighted index.

2. The method of claim 1, wherein: the criteria comprise an image quality criterion, an illumination fitting criterion, and a patrol efficiency criterion.

3. The method of claim 2, wherein: the index corresponding to the image quality criterion comprises a target occlusion rate, a target average size, and an average shooting angle; the index corresponding to the illumination fitting criterion comprises a backlight shooting rate and an average illumination angle; the index corresponding to the patrol efficiency criterion comprises a task completion rate, a preset point number, a task time consumption, and a unit target time consumption.

4. The method of claim 1, wherein, The step of combining subjective and objective weights of the index by using the analytic hierarchy process and the entropy weight method, and evaluating the preset position layout scheme according to the weighted index comprises: determining a subjective weight according to the analytic hierarchy process; determining an objective weight according to the entropy weight method; determining a comprehensive weight according to the subjective weight and the objective weight; for each of the preset position layout schemes, weighting the index according to the comprehensive weight to acquire an evaluation index; selecting a target layout scheme from a plurality of the preset position layout schemes according to the evaluation index.

5. The method of claim 4, wherein, The step of determining a comprehensive weight according to the subjective weight and the objective weight comprises: acquiring an intermediate value corresponding to the index according to an arithmetic square root of a product of the subjective weight and the objective weight corresponding to the same index; acquiring the comprehensive weight of the index corresponding to the intermediate value as the numerator, and the sum of the intermediate values corresponding to each of the indexes as the denominator.

6. An image terminal preset position detection and evaluation system, characterized in that, The system comprises: The target layer is configured to obtain a plurality of preset position layout schemes, including: establishing a space shooting potential normalization matrix; elements in the normalization matrix are shooting potentials corresponding to space points; comparing the shooting potentials with a threshold value, and performing a preliminary screening on the space points according to a comparison result; establishing a single space constraint, and establishing a target function for solving a maximum sum of the shooting potentials based on the single space constraint; performing a fine screening on the target function according to an ant colony algorithm, and obtaining a target solution of the target function; selecting the preset positions from the space points and obtaining the preset position layout schemes according to the target solution; and a shooting potential of a to-be-inspected target at a space point P(x p , y p , z p ) is calculated according to a formula as follows: Wherein, S is the area of the region where the target to be inspected is located, p s is the surface information density, to represent the importance of S, σ s is the area element, and θ is the angle between the preset camera line of sight and the surface normal vector. The smaller the angle is, the more normal the shooting angle is, and the smaller the deformation of the target to be inspected in the picture is. a criterion layer configured to acquire a plurality of criteria for evaluating the preset position layout scheme; an index layer configured to acquire an index corresponding to each of the criteria according to the preset position layout scheme; a scheme layer configured to combine subjective and objective weights of the index by using the analytic hierarchy process and the entropy weight method, and evaluate the preset position layout scheme according to the weighted index.

7. The system of claim 6, wherein, The scheme layer is further configured to determine a subjective weight according to the analytic hierarchy process, determine an objective weight according to the entropy weight method, determine a comprehensive weight according to the subjective weight and the objective weight, for each of the preset position layout schemes, weight the index according to the comprehensive weight to acquire an evaluation index, and select a target layout scheme from a plurality of the preset position layout schemes according to the evaluation index.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor executes the computer program to implement the steps of the method of any one of claims 1 to 5.

9. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 5.

10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 5.

Images