CN116822357A - Photogrammetry station layout planning method based on improved wolf algorithm - Google Patents
Photogrammetry station layout planning method based on improved wolf algorithm Download PDFInfo
- Publication number
- CN116822357A CN116822357A CN202310748723.9A CN202310748723A CN116822357A CN 116822357 A CN116822357 A CN 116822357A CN 202310748723 A CN202310748723 A CN 202310748723A CN 116822357 A CN116822357 A CN 116822357A
- Authority
- CN
- China
- Prior art keywords
- wolf
- photogrammetry
- wolves
- algorithm
- layout
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 241000282461 Canis lupus Species 0.000 title claims abstract description 128
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 63
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000011156 evaluation Methods 0.000 claims abstract description 26
- 238000005457 optimization Methods 0.000 claims abstract description 16
- 238000003064 k means clustering Methods 0.000 claims abstract description 13
- 241000282421 Canidae Species 0.000 claims description 52
- 238000005259 measurement Methods 0.000 claims description 32
- 239000013598 vector Substances 0.000 claims description 26
- 239000011159 matrix material Substances 0.000 claims description 10
- 201000004569 Blindness Diseases 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000002068 genetic effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000005295 random walk Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The application relates to the technical field of photogrammetry, in particular to a photogrammetry station layout planning method based on an improved gray wolf algorithm; firstly, establishing a photogrammetry uncertainty evaluation function; then generating an initial photogrammetry station layout position according to a K-means clustering algorithm; finally, taking the photogrammetry uncertainty evaluation function as an objective optimization function of a wolf algorithm to obtain an optimal photogrammetry station layout, generating an initial photogrammetry station by adopting a kmeans clustering algorithm on the basis of the traditional wolf algorithm, and taking the initial photogrammetry station as an individual of an initial population, so that the wolf algorithm is improved to adapt to the photogrammetry station layout, and the searching speed of the optimal station layout is improved.
Description
Technical Field
The application relates to the technical field of photogrammetry, in particular to a photogrammetry station layout planning method based on an improved gray wolf algorithm.
Background
Because of the advantages of high precision, large measuring range, portability, capability of measuring a plurality of targets simultaneously, and the like, the photogrammetry technology is widely applied to the assembly process of aircraft parts. When the large-size component is subjected to photogrammetry, the measurement accuracy is greatly influenced by the position and the posture of the camera, and the position and the posture layout of the shooting station can influence the performance of a measurement system. In an actual workflow, the position and number of cameras are typically controlled empirically by an operator, with some blindness. When the body quantity of the part to be measured is large, the structure is complex, the constraint conditions are many, the measurement accuracy cannot be guaranteed to be optimal depending on manual experience, or the number of photos is greatly increased to ensure the overlapping degree of the photos, so that serious image data redundancy is formed. Therefore, the method for researching the substation layout planning of the camera realizes the combined solution of the pose of the camera, eliminates blindness of laying the camera depending on manual experience, has great significance for improving measurement precision and reliability, and can efficiently cope with all measurement tasks by implementing one-time planning in the face of multiple-number identical objects to be measured.
Chen Jiayi (research on a large trough type condenser surface shape photogrammetry network planning method, renewable energy, 2016 (3): 7.) designs a photogrammetry station layout planning method based on a genetic algorithm, so that the measurement accuracy of the surface shape is effectively improved, but global optimization is performed by using the genetic algorithm, the problem of data non-uniformity may exist in a random initialization population, the algorithm parallelism is poor, and the global searching capability needs to be improved.
Disclosure of Invention
Aiming at the problems of uneven data or poor initial individual quality and low searching starting point of a random initialization population in the existing intelligent optimization algorithm, the application provides a photogrammetry station layout planning method based on an improved gray wolf algorithm, which comprises the steps of firstly establishing a photogrammetry uncertainty evaluation function; then generating an initial photogrammetry station layout position according to a K-means clustering algorithm; finally, taking the photogrammetry uncertainty evaluation function as a target optimization function of a wolf algorithm to obtain an optimal photogrammetry station layout, and realizing higher-precision station layout planning by determining an optimal station position combination, thereby improving the measurement efficiency.
The application has the following specific implementation contents:
a photogrammetry station layout planning method based on an improved gray wolf algorithm includes the steps that firstly, the reconstruction uncertainty of a target feature point to be measured is determined according to a reconstruction covariance matrix diagonal element matrix of the target feature point to be measured, and a photogrammetry uncertainty evaluation function is built according to the reconstruction uncertainty; then generating an initial photogrammetry station layout position according to a K-means clustering algorithm; and finally, taking the photogrammetry uncertainty evaluation function as a target optimization function of a wolf algorithm, generating an initial photogrammetry station by adopting a K-means clustering algorithm on the basis of the traditional wolf algorithm, and taking the initial photogrammetry station as an individual of an initial population, so that the wolf algorithm is improved to adapt to the photogrammetry station planning, and the optimal station layout can be searched out more quickly.
In order to better realize the application, the photogrammetry station layout planning method based on the improved gray wolf algorithm specifically comprises the following steps:
step 1: establishing a colinear equation set according to coordinate information of a target feature point to be detected, calculating the maximum value of a reconstruction covariance matrix of the target feature point to be detected on a line element, and taking the maximum value as the reconstruction uncertainty of the target feature point to be detected;
step 2: taking the average value of the reconstruction uncertainty of the feature target point to be measured as the spatial reconstruction uncertainty of the current photogrammetry station layout position, and establishing a measurement uncertainty evaluation function;
step 3: classifying the feature points according to a K-means clustering algorithm, respectively calculating the distances from the feature points to the clustering centers, biasing the set distances to the normal direction of the clustering centers corresponding to the shortest distances, and calculating the initial photogrammetry station layout positions;
step 4: and taking the uncertain evaluation function as an objective optimization function of a gray wolf algorithm, calculating an objective function value, and taking the objective position with the maximum objective function value as the optimal photogrammetry station position.
In order to better implement the present application, further, the step 3 specifically includes the following steps:
step 31: determining the number K of clusters, and randomly selecting K characteristic points from the characteristic point set as initial cluster centers;
step 32: clustering and grouping the characteristic points, respectively calculating the distances from the characteristic points to K clustering centers, and if the current characteristic points reach the K th clustering centers i The shortest distance between the clustering centers, the current feature point is divided into the K-th feature point i Clustering groups and calculating a new clustering center;
step 33: and (3) repeating the step (32) until the position of the clustering center is unchanged, obtaining a final clustering center, and calculating the initial photogrammetry station layout position by biasing the final clustering center to a normal direction by a set distance.
To better implement the application, further, the camera pose of the initial photogrammetric substation layout is directed towards the final cluster center.
In order to better implement the present application, further, the step 4 specifically includes the following steps:
step 41: setting initial parameters of a gray wolf algorithm;
step 42: randomly generating N-1 individuals as an initial population of the wolf algorithm, and placing the initial photogrammetry workstation layout position as an individual into the initial population;
step 43: taking the measurement uncertainty evaluation function as an objective optimization function of the gray wolf algorithm, calculating an objective function value of the individual in the initial population, and selecting an optimal solution of the current objective function value as alpha wolf, suboptimal as beta wolf, third optimal as delta wolf and the rest solutions as common wolves;
step 44: setting a position vector of a prey, a position vector of a gray wolf and a random vector, and updating position information of the alpha wolf, the beta wolf and the delta wolf;
step 45: setting a control vector to control the wandering direction of the wolves, setting wandering step length, selecting N/4 individuals from the common wolves to carry out random wandering, calculating the objective function value of the individuals, reserving the first N individuals with the largest objective function value, and updating the positions of the alpha wolves, the beta wolves and the delta wolves;
step 46: judging whether iteration termination conditions are met, if so, combining the positions of the alpha wolf, the beta wolf and the delta wolf as optimal shooting pose to obtain optimal photogrammetry shooting positions; if not, return to step 44.
In order to better implement the present application, further, the step 44 specifically includes the following steps:
step 441: keeping the positions of the alpha wolf, the beta wolf and the delta wolf unchanged, setting a position vector of a game, a position vector and a random vector of a gray wolf, and calculating the distances between a gray wolf individual and the alpha wolf, the beta wolf and the delta wolf by combining the current positions of the alpha wolf, the beta wolf and the delta wolf;
step 442: calculating the distances of the common wolves towards the alpha wolves, the beta wolves and the delta wolves according to the distances among the individual wolves, the alpha wolves, the beta wolves and the delta wolves, and calculating the final position after movement;
step 443: and updating the position information of the alpha wolf, the beta wolf and the delta wolf according to the final position after the movement.
To be better provided withThe application is further realized by that the initial parameters in step 41 comprise population size N and maximum iteration number epsilon max And solving the space range.
In order to better implement the present application, further, the iteration termination condition in step 46 is to determine whether the set maximum number of iterations ε is reached max 。
The application has the following beneficial effects:
(1) According to the application, the K-means clustering method is used for initial station arrangement planning, and the improved gray wolf algorithm is used for optimizing the station position and pose combination, so that the measurement stability and the measurement precision are improved.
(2) According to the application, all measurement tasks are completed under the condition that the layout of the camera station is kept unchanged, and all measurement tasks can be effectively handled by implementing one-time planning in the face of multiple identical-model objects to be measured, so that the method has higher measurement efficiency compared with the traditional method for manually arranging cameras
Drawings
FIG. 1 is a flow chart of a method for planning a layout of a photogrammetry workstation based on the improved wolf algorithm.
Fig. 2 is a schematic diagram of the updating of the position of a common wolf in the process of surrounding a prey in the wolf algorithm according to the embodiment of the application.
Detailed Description
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it should be understood that the described embodiments are only some embodiments of the present application, but not all embodiments, and therefore should not be considered as limiting the scope of protection. All other embodiments, which are obtained by a worker of ordinary skill in the art without creative efforts, are within the protection scope of the present application based on the embodiments of the present application.
In the description of the present application, it should be noted that, unless explicitly stated and limited otherwise, the terms "disposed," "connected," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; or may be directly connected, or may be indirectly connected through an intermediate medium, or may be communication between two elements. The specific meaning of the above terms in the present application will be understood in specific cases by those of ordinary skill in the art.
Example 1:
the embodiment provides a photogrammetry station layout planning method based on an improved gray wolf algorithm, which comprises the steps of firstly determining the reconstruction uncertainty of a target feature point to be detected according to a reconstruction covariance matrix diagonal element matrix of the target feature point to be detected, and establishing a photogrammetry uncertainty evaluation function according to the reconstruction uncertainty; then generating an initial photogrammetry station layout position according to a K-means clustering algorithm; and finally, taking the photogrammetry uncertainty evaluation function as a target optimization function of a gray wolf algorithm, and optimizing the initial photogrammetry workstation layout position to obtain the optimal photogrammetry workstation layout position.
Working principle: in the embodiment, firstly, a photogrammetry uncertainty evaluation function is established; then generating an initial photogrammetry station layout position according to a K-means clustering algorithm; finally, taking the photogrammetry uncertainty evaluation function as a target optimization function of a wolf algorithm to obtain an optimal photogrammetry station layout position, and realizing higher-precision station layout planning by determining an optimal station position combination, thereby improving the measurement efficiency.
Example 2:
this embodiment is described in the form of steps based on the above embodiment 1.
Step 1: establishing a colinear equation set according to coordinate information of a target feature point to be detected, calculating the maximum value of a reconstruction covariance matrix of the target feature point to be detected on a line element, and taking the maximum value as the reconstruction uncertainty of the target feature point to be detected;
step 2: taking the average value of the reconstruction uncertainty of the target point of the feature to be measured as the spatial reconstruction uncertainty of the current photogrammetry station layout, and establishing a measurement uncertainty evaluation function;
step 3: classifying the feature points according to a K-means clustering algorithm, respectively calculating the distances from the feature points to the clustering centers, biasing the set distances to the normal direction of the clustering centers corresponding to the shortest distances, and calculating the initial photogrammetry station layout positions.
Further, the specific step 3 includes the following steps:
step 31: determining the number K of clusters, and randomly selecting K characteristic points from the characteristic point set as initial cluster centers;
step 32: clustering and grouping the characteristic points, respectively calculating the distances from the characteristic points to K clustering centers, and if the current characteristic points reach the K th clustering centers i The shortest distance between the clustering centers, the current feature point is divided into the K-th feature point i Clustering groups and calculating a new clustering center;
step 33: and (3) repeating the step (32) until the position of the clustering center is unchanged, obtaining a final clustering center, and calculating the initial photogrammetry station layout position by biasing the final clustering center to a normal direction by a set distance.
Further, the camera pose of the initial photogrammetric substation layout position is directed towards the final cluster center.
Step 4: and taking the uncertain evaluation function as an objective optimization function of a gray wolf algorithm, calculating an objective function value, and taking the objective position with the maximum objective function value as the optimal photogrammetry station position.
Further, the step 4 specifically includes the following steps:
step 41: setting initial parameters of a gray wolf algorithm;
step 42: randomly generating N-1 individuals as an initial population of the wolf algorithm, and placing the initial photogrammetry workstation layout position as an individual into the initial population;
step 43: taking the measurement uncertainty evaluation function as an objective optimization function of the gray wolf algorithm, calculating an objective function value of the individual in the initial population, and selecting an optimal solution of the current objective function value as alpha wolf, suboptimal as beta wolf, third optimal as delta wolf and the rest solutions as common wolves;
step 44: setting a position vector of a prey, a position vector of a gray wolf and a random vector, and updating position information of the alpha wolf, the beta wolf and the delta wolf;
step 45: setting a control vector to control the wandering direction of the wolves, setting wandering step length, selecting N/4 individuals from the common wolves to carry out random wandering, calculating the objective function value of the individuals, reserving the first N individuals with the largest objective function value, and updating the positions of the alpha wolves, the beta wolves and the delta wolves;
step 46: judging whether iteration termination conditions are met, if so, combining the positions of the alpha wolf, the beta wolf and the delta wolf as optimal shooting pose to obtain optimal photogrammetry shooting positions; if not, return to step 44.
Further, the step 44 specifically includes the following steps:
step 441: keeping the positions of the alpha wolf, the beta wolf and the delta wolf unchanged, setting a position vector of a game, a position vector and a random vector of a gray wolf, and calculating the distances between a gray wolf individual and the alpha wolf, the beta wolf and the delta wolf by combining the current positions of the alpha wolf, the beta wolf and the delta wolf;
step 442: calculating the distances of the common wolves towards the alpha wolves, the beta wolves and the delta wolves according to the distances among the individual wolves, the alpha wolves, the beta wolves and the delta wolves, and calculating the final position after movement;
step 443: and updating the position information of the alpha wolf, the beta wolf and the delta wolf according to the final position after the movement.
In order to better implement the present application, further, the initial parameters in step 41 include population size N, maximum number of iterations ε max And solving the space range.
In order to better implement the present application, further, the iteration termination condition in step 46 is to determine whether the set maximum number of iterations ε is reached max 。
Working principle: according to the embodiment, the initial photogrammetry station is generated by adopting a kmeans clustering algorithm based on a traditional wolf algorithm and is used as an individual of an initial population, so that the wolf algorithm is improved to adapt to photogrammetry station planning, and the optimal station layout can be searched out more quickly.
Other portions of this embodiment are the same as those of embodiment 1 described above, and thus will not be described again.
Example 3:
this embodiment is described in detail with reference to one specific embodiment, as shown in fig. 1 and 2, based on any one of embodiments 1 to 2.
The embodiment mainly comprises the following steps:
step S1: establishing a measurement uncertainty evaluation function: according to the coordinate information of the characteristic points of the target to be detected, a colinear equation system is established, and the maximum value of diagonal elements of the reconstruction covariance matrix of m target points to be detected is calculated as the reconstruction uncertainty sigma of the point i i Under this substation layout, the spatial reconstruction uncertainty of the layout is represented by the average of the reconstruction uncertainties of each target point
Performing normalization processing, and establishing a measurement uncertainty evaluation function:
middle sigma lim Uncertainty is measured for spatial points required for the measurement task.
Step S2: and generating an initial substation layout through a K-means clustering algorithm.
The specific operation of step S2 is: firstly, determining the number K of clusters, and randomly selecting K characteristic points from a characteristic point set to serve as initial cluster centers. Then clustering all the feature points, respectively calculating the distances from each feature point to K clustering centers, if a feature point is from the K th clustering center i The shortest cluster center distance divides the feature pointIs K th i And (5) clustering groups, and calculating a new clustering center after all the clustering groups are grouped. And finally repeating the operation of updating the cluster centers and grouping, and iterating the calculation until the positions of the cluster centers are not changed. The position of the shooting station is calculated by biasing the cluster centers to a certain distance in the normal direction, and the camera gesture points to each cluster center.
Step S3: the optimal layout of the photogrammetry workstations is solved by improving the gray wolf algorithm.
The step S3 specifically comprises the following steps:
step S3.1: parameters are set. Setting a population scale N and the maximum iteration number epsilon max The range of the space is solved.
Step S3.2: initializing a population. N-1 individuals are randomly generated as an initial population, and the station layout generated by clustering in step S2 is placed as one individual into the initial population.
Step S3.3: alpha, beta and delta wolf are selected. And (3) taking the measurement uncertainty evaluation function in the step (S1) as an objective optimization function which is an evaluation standard for the quality degree of the wolf individuals in the optimizing process of the wolf algorithm, calculating the objective function value of each wolf individual in the initial population, and selecting 3 individual positions with the largest function value as alpha, beta and delta wolf positions respectively, wherein the rest wolves are taken as common wolf individuals.
Step S3.4: surrounding the prey. Keeping the positions of alpha, beta and delta wolves unchanged byAnd->Position vector representing prey and position vector of wolf, respectively, < >>And->Representing the current positions of alpha, beta and delta respectively; />Is a random vector, the distance between the individual gray wolves and alpha, beta, delta wolves ∈>The method comprises the following steps of:
the direction and distance of the surrounding motion of the common wolves towards alpha, beta and delta wolves are as follows:
in which A i (wherein i=1, 2, 3) is a coefficient vector, and the calculation formula isa i For the convergence factor>Is [0,1]Random numbers in between;
the final position after movement is:t represents the number of iterations.
And calculating the objective function value of the wolf group individuals, and updating the position information of alpha, beta and delta wolves.
In fig. 2, R represents a convergence radius, and Move represents a moving direction.
Step S3.5: by vectorsThe step is used for controlling the wandering direction of the wolves, the step represents the wandering step length, two variables are random, and an individual selecting N/4 from the common wolves omega is according to the formula: />Random walk behavior occurs, updating individual wolf positions, where X (t) represents the position of the front wolf before walk and X' (t) represents the position of the rear wolf after walk.
And calculating objective function values of all individuals, reserving the first N individuals with larger function values, and updating the positions of alpha, beta and delta wolves.
Step S3.6: and judging the iteration termination condition. Judging whether the maximum iteration number epsilon is reached max If so, outputting the current optimal solution, otherwise, turning to step S3.4.
Working principle: according to the method, a measurement uncertainty evaluation function is used as a basis for judging the quality degree of the station layout, and aiming at the problems that the random initialization population in the intelligent optimization algorithm possibly has uneven data or poor initial individual quality and low search starting point, the K-means clustering method is used for initial station layout planning, the station pose combination is optimized through an improved gray wolf algorithm, and the station layout planning with optimal precision is achieved.
The embodiment has the characteristic of high measurement precision, and by using the embodiment to carry out photogrammetry station layout planning, the theoretical optimal station layout can be obtained, and the measurement precision is higher than that of the traditional mode of manually and empirically arranging stations or randomly arranging stations. The method has the characteristic of high measurement stability, and aiming at the same measurement object, the method can complete all measurement tasks by planning the station layout, and the station layout is kept unchanged. The embodiment has the characteristic of high measurement efficiency, and can efficiently cope with all measurement tasks by implementing one-time planning in the face of multiple-frame identical-model objects to be measured.
Other portions of this embodiment are the same as any of embodiments 1 to 2, and thus will not be described again.
The foregoing description is only a preferred embodiment of the present application, and is not intended to limit the present application in any way, and any simple modification, equivalent variation, etc. of the above embodiment according to the technical matter of the present application fall within the scope of the present application.
Claims (8)
1. A photogrammetry station layout planning method based on an improved gray wolf algorithm is characterized in that firstly, the reconstruction uncertainty of a target feature point to be measured is determined according to a reconstruction covariance matrix diagonal element matrix of the target feature point to be measured, and a measurement uncertainty evaluation function is established according to the reconstruction uncertainty; then generating an initial photogrammetry station layout position according to a K-means clustering algorithm; and finally, taking the photogrammetry uncertainty evaluation function as a target optimization function of a gray wolf algorithm, and optimizing the initial photogrammetry workstation layout position to obtain the optimal photogrammetry workstation layout position.
2. The improved gray wolf algorithm-based photogrammetry substation layout planning method as claimed in claim 1, and specifically comprising the steps of:
step 1: establishing a colinear equation set according to coordinate information of a target feature point to be detected, calculating the maximum value of a reconstruction covariance matrix of the target feature point to be detected on a line element, and taking the maximum value as the reconstruction uncertainty of the target feature point to be detected;
step 2: taking the average value of the reconstruction uncertainty of the target point of the feature to be measured as the spatial reconstruction uncertainty of the current photogrammetry station layout, and establishing a measurement uncertainty evaluation function;
step 3: classifying the feature points according to a K-means clustering algorithm, respectively calculating the distances from the feature points to the clustering centers, biasing the set distances to the normal direction of the clustering centers corresponding to the shortest distances, and generating initial photogrammetry station layout positions;
step 4: and taking the uncertain evaluation function as an objective optimization function of a gray wolf algorithm, calculating an objective function value, determining an optimal shooting station pose combination according to the objective function value, and taking the optimal shooting station pose combination as an optimal shooting station layout position.
3. The method for planning the layout of a photogrammetry station based on the modified gray wolf algorithm of claim 2, wherein the specific step 3 comprises the following steps:
step 31: determining the number K of clusters, and randomly selecting K characteristic points from the characteristic point set as initial cluster centers;
step 32: clustering and grouping the characteristic points, respectively calculating the distances from the characteristic points to K clustering centers, and if the current characteristic points reach the K th clustering centers i The shortest distance between the clustering centers, the current feature point is divided into the K-th feature point i Clustering groups and calculating a new clustering center;
step 33: and (3) repeating the step (32) until the position of the clustering center is unchanged, obtaining a final clustering center, biasing the final clustering center to a normal direction by a set distance, and calculating the initial photogrammetry station layout position.
4. A method of photogrammetry workstation layout planning based on the modified wolf algorithm of claim 3, wherein the camera pose of the initial photogrammetry workstation layout position is directed towards the final cluster center.
5. The method for planning a layout of a photogrammetry station based on the modified gray wolf algorithm of claim 2, wherein the step 4 specifically comprises the steps of:
step 41: setting initial parameters of a gray wolf algorithm;
step 42: randomly generating N-1 individuals as an initial population of the wolf algorithm, and placing the initial photogrammetry workstation layout position as an individual into the initial population;
step 43: taking the measurement uncertainty evaluation function as an objective optimization function of the gray wolf algorithm, calculating an objective function value of the individual in the initial population, and selecting an optimal solution of the current objective function value as alpha wolf, suboptimal as beta wolf, third optimal as delta wolf and the rest solutions as common wolves;
step 44: setting a position vector of a prey, a position vector of a gray wolf and a random vector, and updating position information of the alpha wolf, the beta wolf and the delta wolf;
step 45: setting a control vector to control the wandering direction of the wolves, setting wandering step length, selecting N/4 individuals from the common wolves to carry out random wandering, calculating the objective function value of the individuals, reserving the first N individuals with the largest objective function value, and updating the positions of the alpha wolves, the beta wolves and the delta wolves;
step 46: judging whether iteration termination conditions are met, if so, combining the positions of the alpha wolf, the beta wolf and the delta wolf as optimal shooting pose to obtain an optimal photogrammetry shooting layout position; if not, return to step 44.
6. The method for planning a layout of a photogrammetry workstation based on the modified gray wolf algorithm of claim 5, wherein said step 44 comprises the steps of:
step 441: keeping the positions of the alpha wolf, the beta wolf and the delta wolf unchanged, setting a position vector of a game, a position vector and a random vector of a gray wolf, and respectively calculating the distances between an individual gray wolf and the alpha wolf, the beta wolf and the delta wolf by combining the current positions of the alpha wolf, the beta wolf and the delta wolf;
step 442: calculating the distances of the common wolves towards the alpha wolves, the beta wolves and the delta wolves according to the distances among the individual wolves, the alpha wolves, the beta wolves and the delta wolves, and calculating the final position after movement;
step 443: and updating the position information of the alpha wolf, the beta wolf and the delta wolf according to the final position after the movement.
7. The method for improving the cinematographic substation layout planning in accordance with claim 5, wherein said initial parameters in step 41 include population size N, maximum number of iterations ε max And solving the space range.
8. The method for improving the gray wolf algorithm based on the photogrammetry station layout planning method of claim 7, wherein the iteration termination condition in step 46 is a determination of whether the set maximum number of iterations ε is reached max 。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310748723.9A CN116822357B (en) | 2023-06-25 | 2023-06-25 | Photogrammetry station layout planning method based on improved wolf algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310748723.9A CN116822357B (en) | 2023-06-25 | 2023-06-25 | Photogrammetry station layout planning method based on improved wolf algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116822357A true CN116822357A (en) | 2023-09-29 |
| CN116822357B CN116822357B (en) | 2024-09-10 |
Family
ID=88128674
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310748723.9A Active CN116822357B (en) | 2023-06-25 | 2023-06-25 | Photogrammetry station layout planning method based on improved wolf algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116822357B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010117152A (en) * | 2008-11-11 | 2010-05-27 | Nippon Hoso Kyokai <Nhk> | Position calculation device of photographing camera |
| CN112037285A (en) * | 2020-08-24 | 2020-12-04 | 上海电力大学 | Camera calibration method based on Levy flight and mutation mechanism gray wolf optimization |
| CN114047770A (en) * | 2022-01-13 | 2022-02-15 | 中国人民解放军陆军装甲兵学院 | Mobile robot path planning method for multi-inner-center search and improvement of wolf algorithm |
| CN114608540A (en) * | 2022-03-17 | 2022-06-10 | 中国科学院紫金山天文台 | Measurement network type determining method of digital photogrammetric system |
| CN115113628A (en) * | 2022-08-10 | 2022-09-27 | 天津城建大学 | Routing method of inspection robot based on improved wolf algorithm |
| US20220335733A1 (en) * | 2019-07-30 | 2022-10-20 | University Of Nottingham | Improvements in or relating to photogrammetry |
| CN115540869A (en) * | 2022-09-21 | 2022-12-30 | 河海大学常州校区 | Unmanned aerial vehicle 3D path planning method based on improved Hui wolf algorithm |
| CN116191544A (en) * | 2023-02-21 | 2023-05-30 | 国电南瑞南京控制系统有限公司 | Distributed generation cluster division method based on improved K-means algorithm |
-
2023
- 2023-06-25 CN CN202310748723.9A patent/CN116822357B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010117152A (en) * | 2008-11-11 | 2010-05-27 | Nippon Hoso Kyokai <Nhk> | Position calculation device of photographing camera |
| US20220335733A1 (en) * | 2019-07-30 | 2022-10-20 | University Of Nottingham | Improvements in or relating to photogrammetry |
| CN112037285A (en) * | 2020-08-24 | 2020-12-04 | 上海电力大学 | Camera calibration method based on Levy flight and mutation mechanism gray wolf optimization |
| CN114047770A (en) * | 2022-01-13 | 2022-02-15 | 中国人民解放军陆军装甲兵学院 | Mobile robot path planning method for multi-inner-center search and improvement of wolf algorithm |
| CN114608540A (en) * | 2022-03-17 | 2022-06-10 | 中国科学院紫金山天文台 | Measurement network type determining method of digital photogrammetric system |
| CN115113628A (en) * | 2022-08-10 | 2022-09-27 | 天津城建大学 | Routing method of inspection robot based on improved wolf algorithm |
| CN115540869A (en) * | 2022-09-21 | 2022-12-30 | 河海大学常州校区 | Unmanned aerial vehicle 3D path planning method based on improved Hui wolf algorithm |
| CN116191544A (en) * | 2023-02-21 | 2023-05-30 | 国电南瑞南京控制系统有限公司 | Distributed generation cluster division method based on improved K-means algorithm |
Non-Patent Citations (6)
| Title |
|---|
| 刘佳鸣: "基于灰狼优化的均值聚类三维点云数据简化算法研究", 中国优秀硕士学位论文全文数据库信息科技辑, 15 December 2020 (2020-12-15), pages 138 - 309 * |
| 廖延娜;李梦君;张婧琪;: "K均值聚类-粒子群优化多目标定位算法", 电子设计工程, no. 02, 20 January 2018 (2018-01-20), pages 61 - 65 * |
| 张红伟等: "双目视觉测量网络布局规划技术研究", 长春理工大学学报(自然科学版), no. 44, 15 April 2021 (2021-04-15), pages 27 - 36 * |
| 杨红光;刘建生;: "一种结合灰狼优化和K-均值的混合聚类算法", 江西理工大学学报, no. 05, 15 October 2015 (2015-10-15), pages 88 - 92 * |
| 郭迎钢;李宗春;冯其强;王永强;: "工业摄影测量控制网网形对测量精度的影响研究", 测绘通报, no. 2, 20 September 2016 (2016-09-20), pages 261 - 264 * |
| 陈佳毅;董明利;王君;孙鹏;燕必希;: "大型槽式聚光器面形摄影测量网络规划方法研究", 可再生能源, no. 03, 20 March 2016 (2016-03-20) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116822357B (en) | 2024-09-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108537876B (en) | Three-dimensional reconstruction method, device, equipment and storage medium | |
| CN107703480B (en) | Mixed kernel function indoor positioning method based on machine learning | |
| WO2022134567A1 (en) | External parameter calibration method and apparatus, computer device, and storage medium | |
| CN107067437B (en) | Unmanned aerial vehicle positioning system and method based on multi-view geometry and bundle adjustment | |
| CN108645426B (en) | On-orbit self-calibration method for space target relative navigation vision measurement system | |
| CN107561549A (en) | Method and device for relocating terminal position, terminal and storage medium | |
| CN105224743B (en) | A kind of antenna arrangement optimization on full frequency band based on particle cluster algorithm | |
| CN112907747A (en) | Point cloud data processing method and device, electronic equipment and storage medium | |
| Geng et al. | UAV surveillance mission planning with gimbaled sensors | |
| CN111127548A (en) | Grabbing position detection model training method, grabbing position detection method and grabbing position detection device | |
| CN114897215A (en) | Method for optimizing multi-unmanned aerial vehicle reconnaissance task allocation based on unsupervised learning discrete pigeon flock | |
| CN110955859B (en) | Calculation method of actual flight track aerodynamic parameters based on preset flight track | |
| CN113110412A (en) | Voronoi-APF algorithm-based group robot path planning method | |
| CN110704959B (en) | MOEAD (Metal oxide optical insulator deposition) optimization fixture layout method and device based on migration behavior | |
| KR102319631B1 (en) | Device For Tracing Underwater Object And Controlling Method Thereof | |
| CN118254186A (en) | Hand-eye calibration method, device, electronic equipment and computer readable storage medium | |
| CN116822357B (en) | Photogrammetry station layout planning method based on improved wolf algorithm | |
| CN114581515B (en) | Multi-camera calibration parameter optimization method based on optimal path conversion | |
| Yang et al. | An efficient accelerator for point-based and voxel-based point cloud neural networks | |
| CN112836425A (en) | Cylinder fitting method and device based on particle swarm optimization algorithm | |
| CN109508141B (en) | Redundant point detection method for point cloud data fitting | |
| CN109409594B (en) | Short-term wind power prediction method | |
| CN109540022B (en) | Method for planning and deciding path of flat-cabin robot based on TOF depth camera | |
| CN113192172B (en) | Airborne LiDAR ground point cloud simplification method | |
| CN113065604B (en) | Air target grouping method based on DTW-DBSCAN algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |