CN116663867A - Method, apparatus and medium for monitoring using minimum deployment ball based on genetic algorithm - Google Patents
Method, apparatus and medium for monitoring using minimum deployment ball based on genetic algorithm Download PDFInfo
- Publication number
- CN116663867A CN116663867A CN202310947110.8A CN202310947110A CN116663867A CN 116663867 A CN116663867 A CN 116663867A CN 202310947110 A CN202310947110 A CN 202310947110A CN 116663867 A CN116663867 A CN 116663867A
- Authority
- CN
- China
- Prior art keywords
- monitoring
- control
- balls
- genetic algorithm
- ball
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 87
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 38
- 230000002068 genetic effect Effects 0.000 title claims abstract description 37
- 108090000623 proteins and genes Proteins 0.000 claims abstract description 40
- 230000015654 memory Effects 0.000 claims description 18
- 230000035772 mutation Effects 0.000 claims description 13
- 238000004088 simulation Methods 0.000 claims description 8
- 230000000007 visual effect Effects 0.000 claims description 8
- 238000012360 testing method Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 3
- 239000004744 fabric Substances 0.000 abstract description 4
- 239000002699 waste material Substances 0.000 abstract description 2
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000003780 insertion Methods 0.000 description 2
- 230000037431 insertion Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 229910000831 Steel Inorganic materials 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B20/00—ICT specially adapted for functional genomics or proteomics, e.g. genotype-phenotype associations
- G16B20/20—Allele or variant detection, e.g. single nucleotide polymorphism [SNP] detection
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Molecular Biology (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Genetics & Genomics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Physiology (AREA)
- Multimedia (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Proteomics, Peptides & Aminoacids (AREA)
- Biotechnology (AREA)
- Medical Informatics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
Abstract
The invention discloses a method, equipment and medium for monitoring using a minimum control sphere based on a genetic algorithm, which comprises the following steps: s100, calculating and setting the number of the cloth control balls as n (n is a positive integer) according to the volume of the space and the monitoring volume of the cloth control balls; s200, initializing a population: s210, representing n control balls in a three-dimensional coordinate system according to the S100, randomly generating initial control ball positions as individuals of a population, wherein each individual consists of the positions of the control balls, and the positions represent randomly generated genes by using the three-dimensional coordinate system (x, y, z). The genetic algorithm is used for well solving the problems of huge sample quantity and complex operation, and the dead angle-free monitoring in the space is realized by using the minimum control balls, so that the comprehensive and effective monitoring can be realized under the condition of the minimum control balls, and unnecessary redundancy and waste are reduced.
Description
Technical Field
The invention relates to the technical field of control ball monitoring, in particular to a method, equipment and medium for monitoring a minimum control ball based on a genetic algorithm.
Background
With the development of technology, various types of monitoring are not separated from large factories, commercial buildings or places needing important safety protection. For example, in a steel plant, due to the operation requirement, more large-scale mechanical equipment can be placed, the safety of the operation requirement of the large-scale equipment is higher, and the large-scale equipment needs to be monitored in real time so as to prevent problems from being found in time; and some of the large-scale equipment is placed outdoors, so that the monitoring by using the control ball is more convenient, and the equipment can be randomly moved as required. In addition, some outdoor operations are not equipped with a fixed camera, and only a control ball is used for monitoring. However, when the position of the control ball is arranged, if the place needs both full-range monitoring and cost control, the position of the control ball is mostly and continuously adjusted by a manual mode in the prior art to achieve the optimal shooting position and the minimum control ball is used to save cost, but the manual moving step is extremely troublesome and complex, a great deal of manpower and material resources are needed, and the result is not necessarily accurate.
Disclosure of Invention
In order to solve the technical problems in the background technology, aiming at the complexity of the number of samples, the invention provides a method, equipment and medium which can utilize a genetic algorithm to evaluate the fitness of a population and continuously form a new population for the cross variation of sub-generations according to set conditions, thereby obtaining the monitoring method, equipment and medium based on the genetic algorithm by using the minimum distributed control balls. The specific technical scheme is as follows:
in a first aspect, the invention discloses a method for monitoring using a minimum of control balls based on a genetic algorithm, comprising the steps of:
s100, calculating and setting the number of the distributed control balls as n (n is a positive integer) according to the volume size of the space and the monitoring volume size of the distributed control balls;
s200, initializing a population:
s210, representing n control balls in a three-dimensional coordinate system according to the S100, randomly generating initial control ball positions as individuals of a population, wherein each individual consists of the positions of the control balls, and the positions represent randomly generated genes by using the three-dimensional coordinate system (x, y, z);
s220, for each position of the control ball in each individual, calculating the position in the monitoring range of the control ball according to the position of the control ball and the monitoring radius R; traversing each position (x) , ,y , ,z , ) Calculating the distance d between the position and the position of the control ball; if d is less than or equal to R, the position is represented in the clothThe monitoring range of the control ball;
s230, repeating the step S220 until all positions in the three-dimensional space are traversed, and obtaining all positions in the monitoring range and the non-monitoring range of the distributed control ball;
s300, evaluating fitness: f=Wherein K is the number of positions where d > R in S220, f is the fitness, and the smaller the K value is, the larger the fitness f is defined;
s400, selecting: ranking individuals according to fitness from high to low, and selecting an operator as a parent for roulette;
s500, cross operation: selecting a pair of parent individuals as crossing objects, selecting one or more crossing points for each pair of parent individuals, and exchanging genes of the two parent individuals at the crossing points to form new child individuals;
s600, mutation operation: performing mutation operation on the new offspring individuals, and performing position mutation on the genes at the positions (x, y and z) of the control ball, namely randomly moving the coordinate system of the genes; and/or inserting a new gene, i.e., adding a new control sphere, to form a variant progeny individual;
and S700, repeatedly executing the steps S300 to S600 until the f value is maximum and corresponds to the minimum number of the distributed balls, and outputting the optimal solution at the moment.
Further, the method further comprises the steps of:
s221, according to the euclidean distance calculation formula, d=The method comprises the steps of carrying out a first treatment on the surface of the Where (x, y, z) is the position of the control sphere, (x) , ,y , ,z , ) Is the position to be calculated and d is the distance between the two.
Further, in S210, the position represents a randomly generated gene by a three-dimensional coordinate system (x, y, z), and the generated random coordinate values ensure that they are within the three-dimensional space.
Further, the method further comprises the steps of:
s110, if a target to be monitored is important, selecting a distribution control ball with the best shooting visual angle, positioning and placing the distribution control ball, and randomly generating positions of other distribution control balls; the viewing angle assessment is considered according to the following factors: (1) the size and definition of the target under the view angle of the control ball; (2) occlusion of the target at the viewing angle; (3) whether the motion trail of the target at the viewing angle is easier to track.
Further, the method further comprises the steps of:
s800, performing simulation test on the generated optimal solution, evaluating the performance and effect of the optimal solution according to the simulation test result, and monitoring object recognition accuracy by evaluating coverage rate, overlapping degree and monitoring area.
Further, the method further comprises the steps of:
and S810, if the overlapping degree is higher, expanding or shrinking the monitoring range by adjusting the field angle of one or more control balls, and repeating the steps S200 to S700 by a genetic algorithm to finish the optimal layout screening.
Further, in S500, one or more crossover points are selected, at which genes of two parent individuals are exchanged, further comprising:
the n control balls in each parent are marked with serial numbers in the three-dimensional space, when the cross point is selected, the serial numbers of the control balls are used as units for dividing, and the control balls with each serial number and the corresponding positions (x, y, z) are used as a gene exchange basis.
Further, in S600, a new gene is inserted, i.e., a new control ball is added, to form a variant offspring individual, further comprising:
inserting new genes, arranging the newly added control balls in the three-dimensional space randomly, and giving new serial numbers.
In a second aspect, the present invention provides an electronic device comprising: the system comprises a memory and a processor, wherein the memory is in communication connection with the processor, computer instructions are stored in the memory, and the processor executes the method for monitoring the minimum distributed balls based on the genetic algorithm by executing the computer instructions.
In a third aspect, the present invention also provides a computer readable storage medium storing computer instructions for performing the method of any one of the above described genetic algorithm based minimum-spread ball monitoring.
The beneficial effects of the invention are as follows:
dividing a three-dimensional space into a three-dimensional coordinate system, giving coordinates of each point in the space, randomly placing a ball control in the points in the space, combining a plurality of different placement schemes to form an original population with larger data samples, evaluating the fitness of the formed original population through a genetic algorithm, selecting a population with high fitness for intersection and mutation, thus obtaining a new child population, further calculating the fitness of the child population, and continuously repeating the intersection mutation step until a population with high fitness is selected; the genetic algorithm is used for well solving the problems of huge sample quantity and complex operation, and dead angle free monitoring in the space is realized by using the minimum distributed control balls, the algorithm can be used for approaching an optimal solution according to the given specific conditions, and the optimal solution can be obtained by continuous iterative variation calculation, so that comprehensive and effective monitoring can be realized under the condition of the minimum distributed control balls, and unnecessary redundancy and waste are reduced.
The positions and the number of the control balls are optimized through a genetic algorithm, and the minimum number of the control balls can be adopted, so that the purchase, installation and maintenance cost is reduced.
Through optimizing the position of the distributed control ball, the monitoring visual angle is more comprehensive, the coverage range is wider, the monitoring effect is enhanced, the blind area and the missed monitoring are reduced, and the reliability and the efficiency of monitoring are improved.
The genetic algorithm can be optimized according to different monitoring scenes and requirements, and the positions and the number of the distributed control balls can be flexibly adjusted according to actual conditions, so that the monitoring requirements under different scenes are met.
Drawings
FIG. 1 is a flow chart of a method of monitoring using minimum balls based on a genetic algorithm according to the present invention.
FIG. 2 is another flow chart of a method of the present invention for minimum-sphere monitoring based on genetic algorithm.
FIG. 3 is a further flowchart of a method of using minimum-sphere-distribution monitoring based on a genetic algorithm according to the present invention.
FIG. 4 is a schematic diagram of a method of the present invention for monitoring using a minimum number of control balls based on a genetic algorithm.
Fig. 5 is a schematic block diagram of a minimum-distributed-ball monitoring device based on a genetic algorithm according to the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention. On the contrary, the invention is intended to cover any alternatives, modifications, equivalents, and variations as may be included within the spirit and scope of the invention as defined by the appended claims. Further, in the following detailed description of the present invention, certain specific details are set forth in order to provide a better understanding of the present invention. The present invention will be fully understood by those skilled in the art without the details described herein.
Referring to fig. 1 to 5, in a first aspect, the present invention discloses a method for monitoring using a minimum number of control balls based on a genetic algorithm, comprising the steps of:
s100, calculating and setting the number of the cloth control balls as n (n is a positive integer) according to the volume of the space and the monitoring volume of the cloth control balls;
in this embodiment, the volume of the three-dimensional space and the monitored volume of the ball are calculated in advance, and the number of balls is estimated according to the volumes of the two. For example: a volume of a certain three-dimensional space of 270m 3 The maximum monitoring range of the distributed control ball is 25m 3 Therefore, the number of the required control balls is estimated to be 11; the monitoring range of the control ball is calculated, the monitoring range is regarded as a three-dimensional conical or fan-shaped volume, and the view angle and the monitoring radius of the known control ball can be calculated to obtain the approximate volume value of the monitored space volume. The number of the control balls can be any integer value of which the range is more than or equal to 8 and less than or equal to 15.
S200, initializing a population:
s210, representing n control balls in a three-dimensional coordinate system according to the S100, randomly generating initial control ball positions as individuals of a population, wherein each individual consists of the positions of the control balls, and the positions represent randomly generated genes by using the three-dimensional coordinate system (x, y, z);
in this embodiment, the position of each control ball is represented by a three-dimensional coordinate system (x, y, z), the three-dimensional coordinate system of the control ball is taken as the center, the monitoring space range of the control ball is drawn according to the monitoring radius, the existing horizontal range of the field angle of the control ball is 360 degrees, the vertical range is-30 degrees to 90 degrees, the monitoring space range approximates a sphere, and the sphere can also be understood as a sector-shaped volume.
S220, for each position of the control ball in each individual, calculating the position in the monitoring range of the control ball according to the position of the control ball and the monitoring radius R; traversing each position (x) , ,y , ,z , ) Calculating the distance d between the position and the position of the control ball; if d is less than or equal to R, the position is within the monitoring range of the control ball;
in the present embodiment, if the monitoring range of the ball is regarded as a sphere, and the space in which a small portion is not monitored is ignored, each position (x , ,y , ,z , ) Calculating the distance d between the position and the position of the control ball, and if d is less than or equal to R, indicating that the position is in the monitoring range of the control ball; as shown in fig. 4, the monitoring range of the control ball is regarded as a sphere in the three-dimensional space, and each sphere is marked with a serial number. If d > R, the position is not in the monitoring range of the control ball. If the monitoring range of the control ball is regarded as a sector-shaped volume, and higher monitoring precision is required, points in a part of space fall at the notch of the three-dimensional cone, although d is less than or equal to R, the points are not monitored, so that the points can be marked as Q points by drawing a coverage map of each control ball in the three-dimensional space, and after the coordinates and the placement angle of the control ball are determined, the vacant part space is obtained, and all special points d is less than or equal to R in the vacant part space are regarded as not being monitored; other points d > R than the Q point are considered to be out of the monitoring range of the control ball.
S230, repeating the step S220 until all positions in the three-dimensional space are traversed, and obtaining all positions in the monitoring range and the non-monitoring range of the distributed control ball;
in this embodiment, all positions in all spaces are traversed, a monitored set of position points and an unmonitored set of position points are formed by calculation statistics, and the respective numbers thereof are counted.
S300, evaluating fitness: f=Wherein K is the number of positions where d > R in S220, f is the fitness, and the smaller the K value is, the larger the fitness f is defined;
in this embodiment, there are two results of calculating the K value, the first is to consider the monitoring range of the control ball as a sphere, and K is the sum of the number of positions where d > R; the second is to consider the monitoring range of the control ball as a three-dimensional cone, and then k= (sum of Q points of the vacant part space) + (sum of the positions of d > R). The larger the K value is, the more positions are not monitored, and the current requirement is that dead angle monitoring is avoided as much as possible, and the smaller the adaptability f is, the less the adaptability f is, the current condition is met; conversely, the smaller the K value, the fewer the non-monitored positions, the larger the fitness f, and the closer to the optimal solution the more consistent the current condition. f is in the range of (0, 1), and the closer to 1 is the optimal solution.
S400, selecting: ranking individuals according to fitness from high to low, and selecting an operator as a parent for roulette;
in this embodiment, fitness of each population has been calculated in step S300, the fitness is arranged according to the high-low fitness, and operators are selected as parents according to roulette, wherein roulette selects all operators in parents according to the fitness, calculates probability that each operator is selected in all operators, divides the roulette according to the probability, and then randomly swings the roulette, and selects two parents each time. For example: the fitness of the following populations is calculated to be 0.15, 0.10, 0.08, 0.07, 0.05, 0.02 and 0.01 respectively; table 1 below:
| population group | Degree of fitness | Probability of being selected |
| a | 0.15 | 31.25% |
| b | 0.10 | 20.83% |
| c | 0.08 | 16.67% |
| d | 0.07 | 14.58% |
| e | 0.05 | 10.42% |
| f | 0.02 | 4.17% |
| g | 0.01 | 2.08% |
The probability that each population is selected is calculated according to the fitness ratio of each population, the wheel discs are divided according to the probability, the wheel discs are randomly swung subsequently, two populations are selected as father generation each time, for example, the wheel discs are transferred to the population b and the population c, and then the first father generation population is obtained. Similarly, as many parent populations as possible are generated to facilitate the generation of multiple offspring individuals.
S500, cross operation: selecting a pair of parent individuals as crossing objects, selecting one or more crossing points for each pair of parent individuals, and exchanging genes of the two parent individuals at the crossing points to form new child individuals; as shown in fig. 4, the positions of the control balls with the same serial numbers in the two parent coordinate systems are interchanged, so that single-point cross interchange, multi-point cross interchange, i.e. serial number 1 interchange, or serial number 3 interchange can be realized.
In this embodiment, gene exchange may be performed by single-point crossing, multi-point crossing, uniform crossing, or the like. For example:
assuming that each population has 3 control balls, the parent population is a population b and a population c, wherein the three-dimensional coordinates of the control balls of the population b are (1,5,2), (3,8,7) and (5,3,9) respectively; the three-dimensional coordinates of the control balls of the population c are (2,6,2), (4,3,8) and (7,2,5) respectively; the following table 2 performs single-point crossing and multi-point crossing operations, the single-point crossing selecting the 2 nd crossing point, the multi-point crossing selecting the 1 st and 3 rd crossing points; the above operations may form new offspring individuals. Table 2 below:
| parent population | Single point crossover | Multi-point cross |
| b=（1，5，2）（3，8，7）（5，3，9） | b'=（1，5，2）（4，3，8）（7，2，5） | b'=（2，6，2）（3，8，7）（7，2，5） |
| c=（2，6，2）（4，3，8）（7，2，5） | c'=（2，6，2）（3，8，7）（5，3，9） | c'=（1，5，2）（4，3，8）（5，3，9） |
S600, mutation operation: performing mutation operation on the new offspring individuals, and performing position mutation on the genes at the positions (x, y and z) of the control ball, namely randomly moving the coordinate system of the genes; and/or inserting a new gene, i.e., adding a new control sphere, to form a variant progeny individual;
in this example, the position of the ball position (x, y, z) gene was controlled to make position variation and insert new genes, and the new offspring individuals formed by single point crossover were calculated as shown in table 2 above, for example as shown in table 3 below:
| progeny obtained by single point crossover | Position variation | Insertion of novel genes |
| b'=（1，5，2）（4，3，8）（7，2，5） | b''=（1，8，2）（5，3，8）（7，2，5） | b''=（1，5，2）（4，3，8）（7，2，5）（2，5，6） |
| c'=（2，6，2）（3，8，7）（5，3，9） | c''=（3，6，2）（3，8，9）（5，4，9） | c''=（2，6，2）（3，8，7）（5，3，9）（7，8，9） |
The position variation is carried out on one gene of the new offspring individuals obtained through the crossover operation, and a certain position of a certain gene is randomly changed; the new gene is inserted, namely a new distributed sphere coordinate system is added, the coordinate system is also randomly set, and 1 or more new genes can be inserted. The mutation and insertion of the new gene may be performed simultaneously or separately, and the mutation may be performed on the new offspring individuals by the same method.
And S700, repeatedly executing the steps S300 to S600 until the f value is maximum and corresponds to the minimum number of the distributed balls, and outputting the optimal solution at the moment.
In this embodiment, the above operations are repeated, the fitness f of the variant offspring is calculated, the calculated f value and the number of the control balls used by each variant offspring are counted, and offspring individuals with f values closest to 1 and the minimum number of the control balls are selected, and the optimal solution is obtained.
Preferably, the method further comprises the steps of:
s221, according to the euclidean distance calculation formula, d=The method comprises the steps of carrying out a first treatment on the surface of the Where (x, y, z) is the position of the control sphere, (x) , ,y , ,z , ) Is the position to be calculated and d is the distance between the two.
In this embodiment, the distance from each point in the three-dimensional space to its adjacent control ball is calculated by a distance calculation formula.
Preferably, in S210, the position represents a randomly generated gene by a three-dimensional coordinate system (x, y, z), and the generated random coordinate values ensure that they are within the three-dimensional space.
Preferably, the method further comprises the steps of:
s110, if a target to be monitored is important, selecting a distribution control ball with the best shooting visual angle, positioning and placing the distribution control ball, and randomly generating positions of other distribution control balls; the viewing angle assessment is considered according to the following factors: (1) the size and definition of the target under the view angle of the control ball; (2) occlusion of the target at the viewing angle; (3) whether the motion trail of the target at the viewing angle is easier to track.
In this embodiment, for an object requiring a clear view angle, according to the size and definition of the object under the view angle of the ball, the ball with the highest definition can be selected in advance for positioning, and the surrounding is not shielded; whether the motion track of the target under the visual angle is easier to track or not can be understood that the target is monitored by the control ball, and the coverage of multiple visual angles is considered in the placement of the control ball, so that the motion of the target in different directions is covered as much as possible. The multi-view overlay may provide more comprehensive target information, helping the tracking system to better understand the motion behavior of the target. In the placing process of the control ball, a plurality of areas with overlapped visual angles can be intentionally arranged, so that the influence caused by the loss and shielding of the target in the visual field is reduced, and the tracking stability is improved.
Preferably, the method further comprises the steps of:
s800, performing simulation test on the generated optimal solution, evaluating the performance and effect of the optimal solution according to the simulation test result, and monitoring object recognition accuracy by evaluating coverage rate, overlapping degree and monitoring area.
In this embodiment, the test is performed by simulation means such as computer program simulation or mathematical modeling simulation, and the higher the coverage rate of the monitoring area is, the higher the score is; the less overlap, the higher the score; the higher the accuracy of monitoring object identification, the higher the score to evaluate the optimal model.
Preferably, the method further comprises the steps of:
and S810, if the overlapping degree is higher, expanding or shrinking the monitoring range by adjusting the field angle of one or more control balls, and repeating the steps S200 to S700 by a genetic algorithm to finish the optimal layout screening.
In this embodiment, the field angle of one or more control balls is adjusted, that is, the control balls with different field angles are selected to update and replace by different replacement parameters or different models, and iterative optimization is performed again by a genetic algorithm, so that the overlapping degree is continuously reduced, and the complexity of manual operation is reduced.
Preferably, in S500, one or more crossover points are selected, at which genes of two parent individuals are swapped, further comprising: the n control balls in each parent are marked with serial numbers in the three-dimensional space, when the cross point is selected, the serial numbers of the control balls are used as units for dividing, and the control balls with each serial number and the corresponding positions (x, y, z) are used as a gene exchange basis.
In this embodiment, each of the control balls has its corresponding serial number in space, and the serial numbers are exchanged and the corresponding three-dimensional coordinates are exchanged during the cross selection.
Preferably, in S600, a new gene is inserted, i.e., a new control sphere is added, to form a variant offspring individual, further comprising:
inserting new genes, arranging the newly added control balls in the three-dimensional space randomly, and giving new serial numbers.
In this embodiment, a new control ball is inserted so that the population can meet the body conditions as much as possible under the conditions of continuous change or setting to generate new offspring individuals.
In a second aspect, the present invention provides an electronic device comprising: the system comprises a memory 20 and a processor 10, wherein the memory 20 is in communication connection with the processor 10, computer instructions are stored in the memory 20, and the processor 10 executes the method based on the genetic algorithm and using the minimum distributed ball monitoring according to any one of the above by executing the computer instructions.
In this embodiment, based on the same inventive concept, the present invention further provides an electronic device, where the principle of the method based on the genetic algorithm using the least distributed ball monitoring is the same as or similar to that of the method provided by the present invention, so that the repetition is not repeated. Comprising the following steps: the system comprises a memory 20 and a processor 10, wherein the memory 20 is in communication connection with the processor 10, computer instructions are stored in the memory 20, and the processor 10 executes the method based on the genetic algorithm and using the minimum distributed ball monitoring according to any one of the above by executing the computer instructions.
In this embodiment, the processor 10 may include a central processing unit (Central Processing Unit, CPU), a digital signal processor (Digital Signal Processor, DSP), a network processor (Network Processor, NP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or a combination of the above.
The memory 20 acts as a non-transitory computer readable storage medium that stores non-transitory software programs, non-transitory computer executable programs, and modules. May include Random access Memory (Random AccessMemory, RAM) or Non-Volatile Memory (NVM), such as at least one disk Memory.
In a third aspect, the present invention also provides a computer readable storage medium storing computer instructions for performing the method of any one of the above described genetic algorithm based minimum-spread ball monitoring.
In this embodiment, the storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a Flash Memory (Flash Memory), a Hard Disk (HDD), or a Solid State Drive (SSD); the storage medium may also comprise a combination of memories of the kind described above.
The above embodiments are merely illustrative of the principles of the present invention and its effectiveness, and are not intended to limit the invention. Modifications and variations may be made to the above-described embodiments by those skilled in the art without departing from the spirit and scope of the invention. Accordingly, it is intended that all equivalent modifications and variations of the invention be covered by the claims, which are within the ordinary skill of the art, be within the spirit and scope of the present disclosure.
Claims (10)
1. A method for monitoring using a minimum number of control balls based on a genetic algorithm, comprising the steps of:
s100, calculating and setting the number of the distributed control balls as n (n is a positive integer) according to the volume size of the space and the monitoring volume size of the distributed control balls;
s200, initializing a population:
s210, representing n control balls in a three-dimensional coordinate system according to the S100, randomly generating initial control ball positions as individuals of a population, wherein each individual consists of the positions of the control balls, and the positions represent randomly generated genes by using the three-dimensional coordinate system (x, y, z);
s220, for each position of the control ball in each individual, calculating the position in the control ball monitoring range according to the position of the control ball and the monitoring radius R; traversing each position (x) , ,y , ,z , ) Calculating the distance d between the position and the position of the control ball; if d is less than or equal to R, the position is within the monitoring range of the control ball;
s230, repeating the step S220 until all positions in the three-dimensional space are traversed, and obtaining all positions in the monitoring range and the non-monitoring range of the distributed control ball;
s300, evaluating fitness: f=Wherein K is the number of positions where d > R in S220, f is the fitness, and the smaller the K value is, the larger the fitness f is defined;
s400, selecting: ranking individuals according to fitness from high to low, and selecting an operator as a parent for roulette;
s500, cross operation: selecting a pair of parent individuals as crossing objects, selecting one or more crossing points for each pair of parent individuals, and exchanging genes of the two parent individuals at the crossing points to form new child individuals;
s600, mutation operation: performing mutation operation on the new offspring individuals, and performing position mutation on the genes at the positions (x, y and z) of the control ball, namely randomly moving the coordinate system of the genes; and/or inserting a new gene, i.e., adding a new control sphere, to form a variant progeny individual;
and S700, repeatedly executing the steps S300 to S600 until the f value is maximum and corresponds to the minimum number of the distributed balls, and outputting the optimal solution at the moment.
2. The method of genetic algorithm based minimum-sphere monitoring of claim 1, further comprising the step of:
s221, according to the euclidean distance calculation formula, d=The method comprises the steps of carrying out a first treatment on the surface of the Where (x, y, z) is the position of the control sphere, (x) , ,y , ,z , ) Is the position to be calculated and d is the distance between the two.
3. The method of genetic algorithm-based balloon monitoring according to claim 1, wherein in S210, the positions represent randomly generated genes with a three-dimensional coordinate system (x, y, z), and the generated random coordinate values ensure that they are within a three-dimensional space.
4. The method of genetic algorithm based minimum-sphere monitoring of claim 1, further comprising the step of:
s110, if a target to be monitored is important, selecting a distribution control ball with the best shooting visual angle, positioning and placing the distribution control ball, and randomly generating positions of other distribution control balls; the viewing angle assessment is considered according to the following factors: (1) the size and definition of the target under the view angle of the control ball; (2) occlusion of the target at the viewing angle; (3) whether the motion trail of the target at the viewing angle is easier to track.
5. The method of genetic algorithm based minimum-sphere monitoring of claim 1, further comprising the step of:
s800, performing simulation test on the generated optimal solution, evaluating the performance and effect of the optimal solution according to the simulation test result, and monitoring object recognition accuracy by evaluating coverage rate, overlapping degree and monitoring area.
6. The method of genetic algorithm based minimum-sphere monitoring of claim 5, further comprising the step of:
and S810, if the overlapping degree is higher, expanding or shrinking the monitoring range by adjusting the field angle of one or more control balls, and repeating the steps S200 to S700 by a genetic algorithm to finish the optimal layout screening.
7. The method of genetic algorithm based minimum-spread ball monitoring according to claim 1, wherein in S500, one or more crossover points are selected, at which genes of two parent individuals are swapped, further comprising:
the n control balls in each parent are marked with serial numbers in the three-dimensional space, when the cross point is selected, the serial numbers of the control balls are used as units for dividing, and the control balls with each serial number and the corresponding positions (x, y, z) are used as a gene exchange basis.
8. The method of claim 1, wherein in S600, a new gene is inserted, i.e., a new control sphere is added, to form variant offspring individuals, further comprising:
inserting new genes, arranging the newly added control balls in the three-dimensional space randomly, and giving new serial numbers.
9. An electronic device, comprising: a memory and a processor in communication with each other, the memory having stored therein computer instructions that, upon execution, perform the method of using a minimum of ball-control based on a genetic algorithm as claimed in any one of claims 1 to 8.
10. A computer readable storage medium having stored thereon computer instructions for performing the method of any one of claims 1 to 8 using minimum-spread ball monitoring based on a genetic algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310947110.8A CN116663867A (en) | 2023-07-31 | 2023-07-31 | Method, apparatus and medium for monitoring using minimum deployment ball based on genetic algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310947110.8A CN116663867A (en) | 2023-07-31 | 2023-07-31 | Method, apparatus and medium for monitoring using minimum deployment ball based on genetic algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116663867A true CN116663867A (en) | 2023-08-29 |
Family
ID=87724597
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310947110.8A Pending CN116663867A (en) | 2023-07-31 | 2023-07-31 | Method, apparatus and medium for monitoring using minimum deployment ball based on genetic algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116663867A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108416441A (en) * | 2018-05-10 | 2018-08-17 | 华中科技大学 | A kind of naval vessel opposite bank strike Algorithm of Firepower Allocation based on genetic algorithm |
| CN113489952A (en) * | 2021-06-30 | 2021-10-08 | 电子科技大学 | Video monitoring facility layout method oriented to indoor three-dimensional scene |
| CN115495981A (en) * | 2022-09-20 | 2022-12-20 | 广西电网有限责任公司电力科学研究院 | Thunder and lightning positioning optimization method based on genetic and particle swarm optimization |
| CN115529437A (en) * | 2021-06-25 | 2022-12-27 | 青岛海信智慧生活科技股份有限公司 | Method, device, equipment and medium for determining monitoring equipment arrangement information |
-
2023
- 2023-07-31 CN CN202310947110.8A patent/CN116663867A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108416441A (en) * | 2018-05-10 | 2018-08-17 | 华中科技大学 | A kind of naval vessel opposite bank strike Algorithm of Firepower Allocation based on genetic algorithm |
| CN115529437A (en) * | 2021-06-25 | 2022-12-27 | 青岛海信智慧生活科技股份有限公司 | Method, device, equipment and medium for determining monitoring equipment arrangement information |
| CN113489952A (en) * | 2021-06-30 | 2021-10-08 | 电子科技大学 | Video monitoring facility layout method oriented to indoor three-dimensional scene |
| CN115495981A (en) * | 2022-09-20 | 2022-12-20 | 广西电网有限责任公司电力科学研究院 | Thunder and lightning positioning optimization method based on genetic and particle swarm optimization |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105430664B (en) | It is a kind of to be fitted the method and apparatus that path loss is propagated in prediction based on classification | |
| CN110650482B (en) | Base station equipment planarization optimization layout method based on gridding small-area principle and genetic algorithm | |
| CN112182917B (en) | Multi-objective optimization-based camera device deployment and control optimization method, system, device and storage medium | |
| CN110322038B (en) | Method and equipment for automatically arranging fans based on mesoscale data | |
| CN110084355B (en) | Grid scale optimization method of large-amount interaction particle motion simulation system | |
| CN106250933A (en) | Method, system and the FPGA processor of data clusters based on FPGA | |
| CN110579201A (en) | Flatness evaluation method based on differential evolution algorithm | |
| CN108875936A (en) | The method for solving the minimum distance in three-dimensional space between any two polyhedron | |
| CN116663867A (en) | Method, apparatus and medium for monitoring using minimum deployment ball based on genetic algorithm | |
| CN108596032A (en) | It fights in a kind of video behavioral value method, apparatus, equipment and medium | |
| CN116522565B (en) | BIM-based power engineering design power distribution network planning method and computer equipment | |
| CN115451974B (en) | Power equipment routing inspection path planning method, system, equipment and medium | |
| CN116341231A (en) | Method and device for simulating artificial precipitation catalyst diffusion track, server and storage medium | |
| CN109242141A (en) | A kind of prediction technique and device of commodity stocks quantity | |
| CN115544699A (en) | Submarine cable layout optimization method, device, equipment and medium based on genetic algorithm | |
| CN112418715B (en) | Method and device for generating wind power sequence scene set and storage medium | |
| CN112337093B (en) | Virtual object clustering method and device, storage medium and electronic device | |
| CN108271183A (en) | A kind of neighbor cell optimizing method and device based on original measurement report | |
| CN106446532A (en) | Virtual source intensity configuration method | |
| CN108333940B (en) | Method and device for optimizing designated controller parameters | |
| Vershennik et al. | Communication Network Modeling Taking into Account Different Kinds of Inhomogeneities | |
| TWI826873B (en) | Pesticide spraying planning method and pesticide spraying system | |
| CN116894400B (en) | Spatial combination site selection method based on visual sense network | |
| CN108230015A (en) | A kind of method and device in determining value region | |
| CN117875088B (en) | Special army training simulation method, system and medium under limited environment |
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 |