CN114169227A - High-space coverage tower footing monitoring camera laying method based on particle swarm optimization algorithm - Google Patents
High-space coverage tower footing monitoring camera laying method based on particle swarm optimization algorithm Download PDFInfo
- Publication number
- CN114169227A CN114169227A CN202111397141.8A CN202111397141A CN114169227A CN 114169227 A CN114169227 A CN 114169227A CN 202111397141 A CN202111397141 A CN 202111397141A CN 114169227 A CN114169227 A CN 114169227A
- Authority
- CN
- China
- Prior art keywords
- particle
- iteration
- particle swarm
- tower
- particles
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/25—Design optimisation, verification or simulation using particle-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Molecular Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a high-space coverage tower footing monitoring camera arrangement method based on a particle swarm optimization algorithm, which realizes the highest space coverage observed by the arranged high-space monitoring cameras in a 3D geographic scene. The method mainly comprises the following steps: inputting DEM, base station point data, target observation pattern spots and zoning boundary data, and setting parameters such as population size n, population dimension d, iteration times t and the like. Secondly, initializing the particle swarm population, setting the initial position and speed of the particles and the maximum speed Vmax. And thirdly, judging whether the current iteration algebra reaches an algebra threshold value t, and if not, developing a geographic space coverage analysis algorithm. Updating according to individual fitnessThe velocity and position of each particle in the population. Updating the global speed and position of the particle swarm according to the population fitness. Sixthly, performing the next iteration, circularly performing the step III to output the combined sequence of the optimal individual until reaching the threshold value of the iteration times, and obtaining the optimal solution of the high-altitude monitoring cameras with variable quantity which are combined and distributed on the bases of a plurality of communication iron towers. The method can be widely applied to the global multi-camera arrangement scene, such as: the intelligent traffic system has better application value in practice in the aspects of intelligent traffic, forest fire prevention, urban disaster prevention, natural resource protection monitoring and the like.
Description
Technical Field
The invention belongs to the field of facility configuration space optimization, and particularly relates to a tower footing monitoring camera layout method based on a particle swarm optimization algorithm.
Background
The essence of the layout of the tower footing monitoring cameras is a spatial optimization problem, the spatial optimization is an important branch of geographic information modeling, and in the spatial optimization process, when the dimensionality of spatial optimization solution is continuously increased, the calculation scale and complexity are extremely large, so that the problem is a typical NP-Hard problem. The spatial arrangement of the monitoring cameras is a typical facility space optimization problem. The monitoring cameras are arranged on the tower footing, so that various aspects such as the land types, the use of buildings, the occupation situation and the like can be monitored in real time, but under the multi-target condition that how to use the least monitoring cameras and how to maximize the monitoring range of the monitoring cameras in the regional range, the reasonable arrangement of the positions of the monitoring cameras on the tower footing becomes a difficult point. The intelligent evolutionary algorithm is a random search algorithm set simulating biological evolution in nature or social behaviors in a biological population, is a search strategy of the population and information interaction performed between individuals in the population, is suitable for processing a very complicated nonlinear problem which is difficult to solve by a traditional search method, and can improve the speed of space optimization solution. Common algorithms include genetic algorithm, ant colony algorithm, particle swarm optimization algorithm, simulated annealing algorithm and the like.
The invention is generated based on the background, the particle swarm algorithm has more opportunities to solve the optimal solution, the precision is high, the convergence is fast, and the like.
Disclosure of Invention
The purpose of the invention is as follows: how to find the optimal layout position for the facility is always a difficult problem, and as the solving dimension increases, the calculation amount thereof increases, and finding the optimal solution in a huge solution is an extremely difficult matter. The monitoring cameras are reasonably arranged on the tower footing of the communication iron tower, the monitoring range is improved, and the problem that the overlapping degree belongs to space optimization is reduced. The invention provides a high-space coverage tower-based monitoring camera arrangement method based on a particle swarm optimization algorithm. The invention can improve the monitoring efficiency, save time and labor, reduce the consumption of manpower and financial resources and has better application value in practice.
The technical scheme is as follows: the invention discloses a high-space coverage tower footing monitoring camera layout method based on a particle swarm optimization algorithm, which comprises the following steps of:
Step 2, starting iteration: and based on the set iteration times, updating the positions of the particle individuals and the whole particle swarm in each iteration until the set iteration times t are reached, and ending the process.
Step 3, evaluating the adaptability of the particles: and (4) within the set iteration times t, bringing the position of the particle into the objective function according to the position of the particle after each iteration, and calculating the fitness of the particle. And calculating the fitness of the particles by adopting a geographic space coverage analysis algorithm, wherein the algorithm is performed based on ArcPy, a communication iron tower base station is selected based on the position of the iterated particles, then the height value is extracted to the communication iron tower base station, the communication iron tower base station visibility analysis, the visibility grid surface-turning pattern spot, the polymerization surface pattern spot, the visibility surface pattern spot space polymerization surface and the target observation pattern spot space intersection analysis are performed, and the area of the intersected result pattern spot is calculated to obtain the coverage rate of the target observation pattern spot.
Step 4, updating the speed and the position of the particle individuals and the whole particle swarm: after the primary fitness is calculated, the positions and the speeds of the particles are updated according to the speed of the particles and a position updating formula, the global optimal positions of the particle swarm are updated, the high spatial coverage of the tower-based monitoring cameras is realized by iteratively calculating the adaptive values of the particles after each iteration, and an optimal solution of an indefinite number of high-altitude monitoring cameras which are combined and distributed on the tower bases of a plurality of communication iron towers is obtained.
The invention is based on the space optimization problem of the tower-based monitoring camera layout, adopts the particle swarm optimization algorithm and is assisted by the data processing of the geospatial coverage analysis algorithm, thereby realizing the optimized solution of the combination layout of an indefinite number of high-altitude monitoring cameras on a plurality of communication iron tower base stations, effectively improving the global high-altitude camera observation coverage, saving the camera resources, solving the problems of high overlapping degree of the monitoring camera coverage and neglecting the influence of terrain visibility of the traditional manual decision layout scheme, effectively reducing the subjectivity of the manual decision layout scheme, and being widely applied to the global multi-camera layout scene, such as: the intelligent traffic system has better application value in practice in the aspects of intelligent traffic, forest fire prevention, urban disaster prevention, natural resource protection monitoring and the like.
Further, in the population initialization of step 1, the DEM, base station data, target observation pattern spot, and partition boundary data are input, parameters such as the population size n, the population dimension d, the iteration number t of the particle swarm are set, and the initial position is set as:i represents the first particle, where i is (1,2, … n), and the maximum velocity of the particle is set to VmaxThe search divergence can be prevented and the search step size of each particle can be changed.
Further, iteration is carried out at the beginning of the step 2, the iteration times t are reasonably set according to the iteration times, and the running time of the algorithm is reduced. The selection of the number of iterations can be described as follows:
p is the optimal position of the particle and c is the learning factor.
From the basic iterative expression, one can deduce:
formula (1) and formula (2) are taken together:
the characteristic equation of equation (3) is:
the root of formula (4) is:
when v (0) and p-x (0) are known and c is not 4, the learning factor c1,c2Can be expressed as:
when the accuracy is known, t can be derived immediately. And obtaining the iteration times.
Further, the adaptability of the particles is evaluated in the step 3, the fitness of the particle swarm after each iteration is calculated by taking the area ratio of the coverage of the target observation pattern spots as a target function, and the function adaptive value is calculated by adopting a geographic space coverage analysis algorithm based on automatic data processing calculation of the ArcPy. The algorithm comprises the following steps:
step 3.1, selecting a communication iron tower base station: based on the positions of the particle swarm after iteration, because the positions of the particle swarm after each iteration update of the particle swarm optimization algorithm are in a sequence form and only have 0 and 1, the serial number of the communication iron tower base station corresponding to the position with the value of 1 is found out and used as the layout position of the monitoring camera.
Step 3.2, extracting the elevation value to a communication iron tower footing station: and based on the tower footing monitoring camera selected in the step 3.1, extracting the grid pixel value into a tower footing monitoring camera attribute table based on ArcPy by adopting an ExtractValueToPoints tool in ArcGIS based on the elevation data of the DEM in the research area as the elevation value of the tower footing monitoring camera.
Step 3.3, communication tower base station visibility analysis: and 3.2, setting the Visibility radius of the experimental high-altitude monitoring camera based on the elevation value of the tower-based monitoring camera in the ArcGIS and the ArcPy by adopting the Visibility _3d in the ArcGIS, and carrying out Visibility analysis on the tower height to obtain the Visibility grid data of the communication iron tower-based station.
Step 3.4, visibility grid surface-turning pattern spots and polymerization surface pattern spots: and (3) converting the grid part which is visible in the grid data obtained in the step (3.3) and represents the communication iron tower base station into a surface layer based on ArcPy by adopting RasterToPolygon _ conversion and Aggretepolygons _ cartography in ArcGIS, aggregating the aggregated surface pattern spot Shapefile to remove the cavity part through aggregation operation, eliminating the discrete surface, improving the processing efficiency of the data, and setting the minimum cavity area during aggregation as the square value of the original DEM data resolution.
And 3.5, carrying out space intersection analysis on the space aggregation plane of the visibility surface pattern spot and the target observation pattern spot, and carrying out space intersection analysis on the surface pattern spot Shapefile aggregated in the step 3.4 and the target observation pattern spot by adopting an intersection _ analysis in ArcGIS based on ArcPy. And adding an Area field, calculating the Area of the intersecting surface pattern spot, and further obtaining the coverage rate of the target observation pattern spot. The step can check whether the layout of the tower-based monitoring camera is reasonable and the adaptive value of the particles is large or small.
Further, the position and the velocity of the particle are updated in step 4, and the optimal position of the particle is adjusted according to the update velocity formula and the update position formula of the particle, so as to perform the next iteration.
The update rate formula of the particles is:
in the formula (6), Vi k+1The d-dimension component of the flight velocity vector of the (k + 1) th iteration particle i is represented, W is the inertia weight, and the value of W is generally [0.4,1.2 ]]Which helps to reduce the velocity of each particle and thus improve convergence, c1,c2In order for the acceleration constant to also become a learning factor, c for each particle is updated at the time of updating the velocity1,c2The values are the same, and the data are obtained,indicating the historical optimum position of the ith particle in the kth generation,denoted as global optimum position of the k-th generation.
The updated position formula of the particle is:
in equations (6) and (7), i represents the ith particle, and k represents the number of iterations.For the d-dimension component of the position vector of the (k + 1) -th iteration particle i, the principle of the movement of the particle is shown in fig. 7.
And after the speed of the particles is updated, returning to the step 3, continuously calculating the fitness of the particle swarm, finishing the program output after the iteration times are reached, outputting a combined sequence with an optimal result, and obtaining an optimal solution of a plurality of high-altitude monitoring cameras which are combined and distributed in an indefinite number on the tower foundations of the communication iron towers.
Has the advantages that: compared with the prior art, the invention has the following advantages:
the invention constructs a whole set of algorithm flow for the combined layout of the tower-based monitoring cameras, and develops and forms a complete software tool based on Python, Arcpy, Numpy, Matplotlib and the like. The algorithm module defines a complete visibility analysis target function, and various reasonable layout schemes can be selected through iteration of the particle swarm optimization algorithm and diversity of particle swarms. Compared with the traditional method of relying on artificial subjective selection and configuration of camera point locations, the algorithm module has the following advantages: the configuration process is quantified and calculated, the subjectivity of the traditional mode is reduced, and the quality precision of configuration is improved. Secondly, the efficiency of configuring the NP-Hard layout problem is improved by applying the particle swarm optimization. The limitation that the traditional method cannot analyze the visible shielding of each camera due to the influence of the terrain is broken through, and effective visible analysis can be realized. And fourthly, the method can relieve the defects of time and labor consumption of the manual site selection method.
Drawings
FIG. 1 Experimental flow sheet
FIG. 2 iterative convergence diagram of population
FIG. 3 is a diagram of selecting a communication iron tower base station and extracting elevation values from the selected communication iron tower base station
FIG. 4 is a grid view of a tower base station point visibility grid
FIG. 5A polymeric surface view
FIG. 6 analysis diagram of intersection of a visibility surface pattern spot space aggregation surface and a target observation pattern spot space
FIG. 7 is a schematic diagram of particle movement
FIG. 8 is a diagram showing the layout position results of layout points
FIG. 9 is a view showing the results of monitoring cultivated land
Detailed Description
The technical solution of the present invention is described in detail below, but the scope of the present invention is not limited to the embodiments.
As shown in fig. 1, the method for laying high-spatial coverage tower-based surveillance cameras based on the particle swarm optimization algorithm of the present invention includes the following experimental steps:
And 2, starting iteration. Population iteration, wherein the fitness value of the objective function converges in the process as shown in fig. 2, the fitness value comprises an optimal value and an average value of each generation, the iteration times t are calculated according to formulas (1) - (5), and the particle swarm can be simplified as follows:
p is the optimal position of the particle and c is the learning factor.
From the basic iterative expression, one can deduce:
formula (1) and formula (2) are taken together:
the characteristic equation of equation (3) is:
the root of formula (4) is:
when v (0) and p-x (0) are known and c is not 4, the learning factor c1,c2Can be expressed as:
when the accuracy is known, t can be derived immediately. And obtaining the iteration times. Through calculation, in the experiment, the iteration times t take the value of 100.
And 3, evaluating the adaptability of the particles, and calculating the adaptability of the particle swarm after each iteration by taking the proportion of the observation farmland pattern spot range as a target function. The function adaptation value is mainly judged by the effect of the processed ArcPy data. The method comprises the following steps:
step 3.1, selecting the layout points of the iron tower base station: based on the solution sequence obtained in the step 2, only two values of 0 and 1 are included in the solution sequence, the index of the position corresponding to the value 1 is the point sequence number of the base station, namely the point ID, the communication iron tower base station corresponding to the point sequence number is selected based on ArcPy by adopting a Select _ analysis tool in the ArcGIS, and the selected communication iron tower base station is exported to be a sharefile file to be used as the layout point selected in the iteration.
Step 3.2, extracting the elevation value to a communication iron tower footing station: based on the step 3.1, a point Shapefile is distributed, DEM grid pixel values are extracted to a communication iron tower base station based on ArcPy by adopting an ExtractValueToPoints tool in ArcGIS based on the elevation data of DEM in Jiangyin as the elevation value of a tower base monitoring camera, the grid pixel values are stored in a RASTERVALU field, and the selected communication iron tower base station and the elevation value of the base station are shown in figure 3.
Step 3.3, communication tower base station visibility analysis: and (3) carrying out Visibility analysis by adopting Visibility _3d in ArcGIS based on ArcPy and setting the Visibility radius of the high-altitude monitoring camera to be 2500m and the tower height to be 35 m and the elevation value of the communication iron tower base station obtained in the step 3.2 to obtain Visibility grid data.
Step 3.4, visibility grid surface-turning pattern spots and polymerization surface pattern spots: converting the grid part with the value of the vulue field not being 0 in the grid data obtained in the step 3.3 into a surface layer by adopting RasterToPolygon _ conversion and Aggretepolygons _ cartography in ArcGIS based on ArcPy, wherein the surface map spot of the visible part is shown in figure 4, removing the hole part through aggregation operation, eliminating the discrete surface, improving the processing efficiency of the data, setting the minimum hole area as the square value of the original DEM data, and setting the DEM data resolution as 12.5m, so that the minimum hole area is set as 156.25m2The aggregated result is exported as a Shapefile, and the effect of aggregating the surface pattern spots of the visible part is shown in FIG. 5.
And 3.5, carrying out intersection analysis on the visibility surface pattern spot space aggregation surface and the cultivated land pattern spot space, and carrying out intersection analysis on the surface layer pattern file aggregated in the step 3.4 and the cultivated land pattern spot to obtain an intersection result pattern file by adopting an intersection _ analysis in ArcGIS based on ArcPy. And adding an Area field, calculating the geometry, and calculating the Area of the pattern spot of the result after the intersection analysis so as to obtain the observable coverage rate of the pattern spot of the cultivated land. The result of local intersection of the aggregate surface pattern spot and the arable land pattern spot is shown in fig. 6.
And 4, updating the particles and the speed and the position of the particles, adjusting the optimal position of the particles according to the update speed formula and the update position formula of the particles, and performing the next iteration.
The update rate formula of the particles is:
in the formula (6), Vi k+1Representing the d-dimension component of the flight velocity vector of the (k + 1) -th iteration particle i, wherein W is the inertia weight, and the value of W is generally [0.4,1.2 ]]In the present invention, the value of W is taken to be 0.8, c1,c2In order that the acceleration constant also becomes a learning factor, c in the present invention1,c2The value of 2 is taken as the index,indicating the historical optimum position of the ith particle in the kth generation,denoted as global optimum position of the k-th generation.
The updated position formula of the particle is:
in equations (6) and (7), i represents the ith particle, and k represents the number of iterations.Is the d-dimension component of the (k + 1) -th iteration particle i position vector. The schematic diagram of particle movement is shown in fig. 7.
And after the speed of the particles is updated, returning to the step 3, continuously calculating the fitness of the particle swarm, finishing the program output after the iteration times are reached, outputting a combined sequence with the optimal result, and obtaining an optimal solution of a plurality of high-altitude monitoring cameras which are combined and distributed in an indefinite number on the tower foundations of the communication iron towers.
After the program is finished, obtaining a combined solution sequence of the optimal individual, namely the layout points of the high-altitude monitoring camera, wherein the result of the selected layout points is shown in fig. 8, performing visibility analysis, grid surface conversion and aggregation surface according to the optimal solution sequence, and obtaining cultivated land pattern spots observable at 100 layout point positions after intersection analysis is shown in fig. 9. As shown in fig. 8 and 9, the layout points obtained by the particle swarm optimization algorithm are reasonable in position. The number of the distribution points is small in the region with small cultivated land area (such as the region close to the river in the north part and the region at the edge of the south part), most of the distribution points are selected in the region around the town and with dense cultivated land coverage, the distance between the distribution points is also set reasonably, and the problem of high overlapping of adjacent distribution points is greatly reduced. And through calculation, high-altitude monitoring cameras are arranged according to the arrangement points selected from the optimal solution sequence, 30% cultivated land in a certain city can be monitored, the area covering the cultivated land can be observed actually through quantitative evaluation of results, and the cultivated land shielding condition caused by the influence of terrain visibility can be eliminated. The experimental results show that the method is reasonable and reliable, can solve the problems of high overlapping degree and neglect of terrain visibility influence of the coverage area of the monitoring camera of the traditional manual decision layout scheme, effectively reduces the subjectivity of the manual decision layout scheme, can effectively improve the global high-altitude camera observation coverage area, and saves camera resources.
Claims (5)
1. A high-space coverage tower footing monitoring camera layout method based on a particle swarm optimization algorithm is characterized by comprising the following steps: the particle swarm optimization algorithm based on the method is high in implementation speed, few in adopted parameters, and within the set iteration times t, data processing is assisted by a geographic space coverage analysis algorithm, so that the distribution position of the tower-based monitoring camera can be rapidly calculated, and high coverage of a monitored area is realized. The method comprises the following steps:
step 1, population initialization: inputting DEM, base station data, target observation pattern spot and zoning boundary data, setting the size n of the population scale, the dimension d of the population, the iteration times t, the initial position and the initial speed of the particle swarm and the maximum speed V of the particle movementmax。
Step 2, starting iteration: and based on the set iteration times t, updating the speed and the position of the particle individuals and the whole particle swarm in each iteration until the set iteration times are reached, and ending the process.
Step 3, evaluating the adaptability of the particles: and (4) within the set iteration times t, introducing the positions of the particles and the whole particle swarm after each iteration into an objective function, and calculating the fitness of the particles. Calculating the fitness of the particles based on a geographic space coverage analysis algorithm, specifically comprising: GIS gates a communication iron tower point, extracts an elevation value to a communication iron tower base station, performs visibility analysis on the communication iron tower base station point, converts a visibility grid into a visibility surface pattern spot, performs spatial aggregation on the visibility surface pattern spot to eliminate a discrete surface, performs spatial intersection analysis on a visibility surface pattern spot spatial aggregation surface and a target observation pattern spot to obtain a result pattern spot, finally counts the area of the result pattern spot, and calculates the adaptive value of a population individual.
Step 4, updating the speed and the position of the particle individuals and the whole particle swarm: after the fitness of one round of particles is calculated, the speed and the position of each particle in the particle swarm are updated according to the individual fitness of the swarm, the global speed and the position of the particle swarm are updated according to the population fitness, the adaptive value of the particle swarm after each iteration is calculated through iteration, the high spatial coverage of the tower base monitoring cameras is achieved, and an optimal solution of an indefinite number of high-altitude monitoring cameras which are combined and distributed on a plurality of communication iron tower base stations is obtained.
2. The particle swarm optimization algorithm-based high-spatial-coverage tower-based monitoring camera layout method according to claim 1, characterized in that: in the initialization of the step 1, the population size n, the population dimension d and the iteration number t of the particle swarm are input, and the initial positions of the particles are set as follows:where i (i ═ 1,2, …, n) denotes the particle sequence, with an initial velocity ofSetting the maximum velocity of the particles to VmaxSetting the maximum speed is advantageous in preventing the search from diverging, and the search step size of each particle can be changed.
3. The particle swarm optimization algorithm-based high-spatial-coverage tower-based monitoring camera layout method according to claim 1, characterized in that: and (3) starting iteration in the step (2), wherein if the iteration times in the step (1) are set reasonably, the running time of the algorithm can be reduced. The selection of the number of iterations can be described as follows:
where P is the optimal position of the particle and c is the learning factor.
From equation (1) one can deduce:
formula (1) and formula (2) are taken together:
the characteristic equation of equation (3) is:
the root of formula (4) is:
when v (0) and p-x (0) are known and c is not 4, the learning factor c1,c2Can be expressed as:
when the accuracy is known, t can be obtained immediately, i.e. the number of iterations.
4. The particle swarm optimization algorithm-based high-spatial-coverage tower-based monitoring camera layout method according to claim 1, characterized in that: and 3, evaluating the adaptability of the particles, calculating the adaptability of the particle swarm after each iteration by taking the area ratio of the coverage of the target observation pattern spots as a target function, and developing the calculated adaptability of the particles based on a geographic space coverage analysis algorithm, wherein the steps are as follows:
step 3.1, selecting a communication iron tower base station: based on the position of the particle swarm after each iteration, because the position of the particle swarm after each iteration update of the algorithm is in a sequence form and only has 0 and 1, the position of the communication tower base station corresponding to the position with the value of 1 is found out and used as the layout position of the monitoring camera.
Step 3.2, extracting the elevation value to a communication iron tower footing station: and 3.1, based on the tower footing monitoring camera selected in the step 3.1, extracting the DEM grid pixel element value into a communication iron tower base station point attribute table as the elevation value of the tower footing monitoring camera on the basis of the DEM elevation data of the research area.
Step 3.3, communication tower base station visibility analysis: and 3.2, based on the height value of the tower-based monitoring camera in the step 3.2, carrying out visibility analysis on the tower height of the iron tower according to the visibility radius of the high-altitude monitoring camera to obtain visibility grid data of the particle swarm.
Step 3.4, visibility grid surface-turning pattern spots and polymerization surface pattern spots: and (3) converting the visible raster part in the raster data obtained in the step (3.3) into a surface layer, aggregating the surface layer, removing a cavity part through aggregation operation, eliminating a discrete surface, improving the processing efficiency of the data, and setting the minimum cavity area as a square value of the resolution of the original DEM data during aggregation.
And 3.5, carrying out intersection analysis on the space aggregation surface of the visibility surface pattern spots and the target observation pattern spots, and superposing the space aggregation surface pattern spots aggregated in the step 3.4 and the target observation pattern spots. And calculating the area of the intersected result image spot to obtain the coverage rate of the target observation image spot.
5. The particle swarm optimization algorithm-based high-spatial-coverage tower-based monitoring camera layout method according to claim 1, characterized in that: and 4, updating the positions and the speeds of the particles, adjusting the individual positions of the particles according to the updating speed formula and the updating position formula of the particles, further adjusting the positions and the speeds of the particle swarm, and performing the next iteration.
The update rate formula of the particles is:
in the formula (6), the reaction mixture is,representing the d-dimension component of the flight velocity vector of the (k + 1) -th iteration particle i, wherein W is the inertia weight, and the value of W is generally [0.4,1.2 ]]Which helps to reduce the velocity of each particle and thus improve convergence, c1,c2In order for the acceleration constant to also become a learning factor, c for each particle is updated at the time of updating the velocity1,c2The values are the same, and the data are obtained,indicating the historical optimum position of the ith particle in the kth generation,denoted as global optimum position of the k-th generation.
The updated position formula of the particle is:
in equations (6) and (7), i represents the ith particle, and k represents the number of iterations.For the d-dimension component of the position vector of the (k + 1) -th iteration particle i, the principle of the movement of the particle is shown in fig. 7.
And after the speed of the particles is updated, returning to the step 3, continuously calculating the fitness of the particle swarm, finishing the program output after the iteration times are reached, outputting a combined sequence with an optimal result, and obtaining an optimal solution of a plurality of high-altitude monitoring cameras which are combined and distributed in an indefinite number on the tower foundations of the communication iron towers.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111397141.8A CN114169227A (en) | 2021-11-23 | 2021-11-23 | High-space coverage tower footing monitoring camera laying method based on particle swarm optimization algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111397141.8A CN114169227A (en) | 2021-11-23 | 2021-11-23 | High-space coverage tower footing monitoring camera laying method based on particle swarm optimization algorithm |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114169227A true CN114169227A (en) | 2022-03-11 |
Family
ID=80480543
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111397141.8A Pending CN114169227A (en) | 2021-11-23 | 2021-11-23 | High-space coverage tower footing monitoring camera laying method based on particle swarm optimization algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114169227A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118233224A (en) * | 2024-05-27 | 2024-06-21 | 湖南警察学院 | Method and device for tracing block chain of emergency |
-
2021
- 2021-11-23 CN CN202111397141.8A patent/CN114169227A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118233224A (en) * | 2024-05-27 | 2024-06-21 | 湖南警察学院 | Method and device for tracing block chain of emergency |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114926749B (en) | Near-surface atmospheric pollutant inversion method and system based on remote sensing image | |
CN108227041B (en) | Horizontal visibility forecasting method based on site measured data and mode result | |
CN106780089B (en) | Permanent basic farmland planning method based on neural network cellular automaton model | |
CN103745436B (en) | LiDAR point cloud data shape filtering method based on regional prediction | |
CN108388250B (en) | Water surface unmanned ship path planning method based on self-adaptive cuckoo search algorithm | |
CN109359166B (en) | Space growth dynamic simulation and driving force factor contribution degree synchronous calculation method | |
CN106056591A (en) | Method for estimating urban density through fusion of optical spectrum image and laser radar data | |
CN114501530B (en) | Method and device for determining antenna parameters based on deep reinforcement learning | |
CN114462316B (en) | Air quality optimization simulation method for homeland space planning | |
CN112100921A (en) | Method for acquiring wind resource and wind speed based on WRF and random forest | |
CN103295080A (en) | Three-dimensional path programming method based on elevation diagram and ant colony foraging | |
CN106780586A (en) | A kind of solar energy potential evaluation method based on ground laser point cloud | |
KR20220095092A (en) | Forest fire susceptibility mapping method and apparatus using artificial intelligence | |
CN112462805A (en) | 5G networked unmanned aerial vehicle flight path planning method based on improved ant colony algorithm | |
CN114169227A (en) | High-space coverage tower footing monitoring camera laying method based on particle swarm optimization algorithm | |
CN110175793B (en) | Artificial precipitation aircraft route design method based on ground demand analysis | |
CN109360231B (en) | Sea ice remote sensing image simulation method for generating confrontation network based on fractal depth convolution | |
Kim et al. | mmWave path loss modeling for urban scenarios based on 3D-convolutional neural networks | |
Chen et al. | Design and implementation of a novel internet of things irrigation system with a precision irrigation robot | |
CN108510097B (en) | Power transmission line corridor snow disaster monitoring method and system based on satellite remote sensing | |
CN117170408A (en) | Photovoltaic panel site inspection path intelligent planning system and method based on unmanned aerial vehicle | |
CN117523398A (en) | Remote sensing image land coverage evolution time-space diagram analysis method for self-adaptive migration training sample | |
CN110135103B (en) | Method and system for simulating urban natural ventilation potential by adopting water flow | |
CN109784225B (en) | Geographical space mode identification method based on reachable space | |
Zhang et al. | Research on complete coverage path planning for unmanned surface vessel |
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 |