CN115909083B - Satellite earth observation discrete interest point clustering planning method and device - Google Patents
Satellite earth observation discrete interest point clustering planning method and device Download PDFInfo
- Publication number
- CN115909083B CN115909083B CN202211348216.8A CN202211348216A CN115909083B CN 115909083 B CN115909083 B CN 115909083B CN 202211348216 A CN202211348216 A CN 202211348216A CN 115909083 B CN115909083 B CN 115909083B
- Authority
- CN
- China
- Prior art keywords
- interest
- interest point
- value
- satellite
- clustering
- 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.)
- Active
Links
Classifications
-
- 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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The invention discloses a satellite earth observation discrete interest point clustering planning method and device, and belongs to the technical field of satellite earth observation task planning. The method comprises the following steps: acquiring information of interest points in a target area; wherein the information includes: longitude, latitude, and interest value; clustering the interest points based on the information, and acquiring the interest degree of each category in the clustering result; according to satellite Sat k Acquiring the satellite Sat k Stripe in the target area kg And through the satellite Sat k Whether or not to observe the stripe kg Obtaining the strip script kg The value x of the decision variable of (2) kg The method comprises the steps of carrying out a first treatment on the surface of the Based on the interestingness of the categories and the value x of the decision variable kg Maximizing all satellites Sat k And observing the interest degree sum of the target area to obtain an interest point clustering planning result. The method reduces the calculation complexity of the clustering planning algorithm and can achieve higher satellite observation benefits.
Description
Technical Field
The invention relates to a satellite earth observation discrete interest point clustering planning method and device, and belongs to the technical field of satellite earth observation task planning.
Background
In order to improve the utilization efficiency of effective satellite resources, the earth observation activities of satellites need to be reasonably arranged, so that an efficient task execution scheme is formed. The process needs to search the execution sequences of a large number of tasks under various constraint conditions such as a satellite platform and the like, and is a complex combination optimization problem. The current satellite task planning implementation needs to be calculated by a ground task planning center according to various constraints such as task characteristics, a satellite visible time window, a satellite platform load and the like after a task request is received, a planned result instruction is uploaded to a satellite, and the satellite executes a ground observation task according to the uploaded instruction.
When the number of earth observation tasks is huge, such as a large number of points of interest in discrete distribution, the execution sequence of the tasks is quite huge, and the optimization complexity can be increased drastically with the increase of the points of interest. Although merging points of interest with similar geographic locations can reduce the number of tasks to be planned, how to select a feasible merging scheme will directly affect the effect of preprocessing the points of interest and task planning.
Disclosure of Invention
The invention provides a satellite earth observation discrete interest point clustering planning method and device. On the basis, task planning and solving are carried out on all clustered circular areas, so that the computational complexity of a planning algorithm is reduced, and the areas where key interest points appear can be preferentially observed with high probability so as to achieve higher overall observation benefits.
In order to achieve the above purpose, the invention adopts the following technical scheme:
a method for clustering and planning discrete points of interest of satellite earth observation, the method comprising:
acquiring information of interest points in a target area; wherein the information includes: longitude, latitude, and interest value;
clustering the interest points based on the information, and acquiring the interest degree of each category in the clustering result;
according to satellite Sat k Acquiring the satellite Sat k Stripe in the target area g And through the satellite Sat k Whether or not to observe the stripe g Obtaining the strip script g The value x of the decision variable of (2) kg ；
Based on the respectiveInterest level of category and value x of the decision variable kg Maximizing all satellites Sat k And observing the interest degree sum of the target area to obtain an interest point clustering planning result.
Further, the clustering the interest points based on the information, obtaining the interest degree of each category in the clustering result, includes: selecting any interest point from the current interest point set as a circle center;
generating a circle C by taking a set value as a radius i And is determined to be located in the circle C i All the interest points in the map are generated into an interest point set
According to the interest point setInformation of interest points in the circle C is updated i Until the distance between the circle center positions updated twice is smaller than a threshold value, obtaining a interest point subset based on the updated circle center positions;
acquiring the interest degree of the interest point subset based on the interest value of each interest point in the interest point subset;
deleting the interest point subset from the current interest point set, and judging whether the updated interest point set is an empty set or not;
returning to the current interest point set and selecting any interest point as a circle center under the condition that the updated interest point set is not an empty set;
and outputting the interestingness of each interest point subset under the condition that the updated interest point set is an empty set.
Further, the method comprises the steps ofLongitude and latitude of interest point in the circle C, updating the circle C i Is a center of a circle of (a), comprising:
based on the instituteThe interest point setLongitude and interest value of interest point in the center, and calculating longitude of new circle center position +.> Wherein x is j Longitude, w representing the jth point of interest j An interest value representing the jth interest point, n representing the set of interest points +.>The number of points of interest;
based on the interest point setThe latitude and interest value of the interest point in the center of the circle, and calculating the latitude of the new circle center position> Wherein y is j Representing the latitude of the jth point of interest.
Further, said passing said satellite Sat k Whether or not to observe the stripe g Obtaining the value x of the decision variable kg Comprising:
at the satellite Sat k Observing the strip g In the case of (a), the value x of the decision variable kg ＝1；
At the satellite Sat k The strip is not observed g In the case of (a), the value x of the decision variable kg ＝0。
Further, the interest level based on the respective categories and the value x kg Maximizing all satellites Sat k Observing the target areaThe sum of the interestingness to obtain the interest point clustering planning result comprises the following steps:
based on the interestingness and the value x kg Constructing an objective function to be optimized Wherein S represents the satellite Sat k G represents the number of the stripe g Quantity v of (v) i Representing corresponding circle C i Is the interest level of (2);
setting constraint conditions of the objective function;
and optimizing the objective function to be optimized by using a particle swarm algorithm to obtain an interest point clustering planning result.
Further, the constraint condition of the objective function includes:
the satellite Sat k Is a constraint on the observed quantity of (a); wherein the observed quantity constraint indicates that each circular area can only be used by the satellite Sat at most in a planned time interval k Observing for one time;
and, a step of, in the first embodiment,
the satellite Sat k Is a time constraint of imaging; wherein the imaging time constraint represents the satellite Sat k Run over the entire scheduling time range, any of the stripe strips g Must meet imaging time requirements;
and, a step of, in the first embodiment,
the satellite Sat k Is limited by the side swing angle; wherein the yaw angle constraint indicates that the satellite Sat is within a planned time interval k Only one strip under the side swing angle can be selected when the single clustering circle is passed;
and, a step of, in the first embodiment,
the satellite Sat k Is not limited by the storage capacity of the storage device.
Further, the optimizing the objective function to be optimized by using a particle swarm algorithm to obtain a point of interest clustering planning result includes:
for the satellite Sat k With the strip g Initializing;
calculating the number of satellites, the number of corresponding target areas and related constraints as system variables, correcting the variables against the constraints, and taking the sum of the maximum interestingness of the calculated system as a current objective function value;
determining an optimal combination pbest of the current satellite and the strip according to the objective function;
the optimal combination gbest of the satellite and the strip is selected from the optimal combination pbest of all the satellites and the strip in the iteration;
judging whether the maximum iteration times are reached;
returning to the step of calculating the satellite number, the corresponding target area number and the related constraint as system variables under the condition that the maximum iteration number is not reached, and correcting the variables against the constraint to calculate the maximum weight sum of the system as the current objective function value;
and under the condition that the maximum iteration number is reached, taking the optimal combination gbest of the satellite and the strip as a ground observation planning result.
A satellite earth observation discrete point of interest cluster planning apparatus, the apparatus comprising:
the information acquisition module is used for acquiring information of interest points in the target area; wherein the information includes: longitude, latitude, and interest value;
the interest point clustering module is used for clustering the interest points based on the information and acquiring the interest degree of each category in the clustering result;
the variable computing module is used for computing the variable according to the satellite Sat k Acquiring the satellite Sat k Stripe in the target area g And through the satellite Sat k Whether or not to observe the stripe g Obtaining the value x of the decision variable kg ；
A cluster planning module for based on the interestingness of each class and the value x kg Maximizing all satellites Sat k ObservationAnd obtaining the interest point clustering planning result by the interest degree sum in the target area.
A storage medium having a computer program stored therein, wherein the computer program is arranged to perform the satellite earth observation discrete point of interest cluster planning method described above when run.
An electronic device comprising a memory and a processor, the memory having stored therein a computer program, the processor being arranged to run the computer program to perform the satellite earth observation discrete point of interest cluster planning method described above.
Compared with the prior art, the invention has the advantages that:
1. after the clustering process, the area distribution of the discrete interest points is more clear, and the clustering number is far smaller than the number of the interest points, so that the calculation efficiency of satellite observation task planning is higher.
2. The clustering process adjusts the center of the clusters according to the importance of each interest point, so that more important interest points are located at the center of the cluster area, and the more important interest points are observed with higher probability.
3. The clustering method has the advantages that the number of the clusters is not required to be determined in advance, the processing efficiency is high, and a large number of discrete ground interest points can be converged quickly.
Drawings
FIG. 1 is a flow chart of a method for clustering and planning discrete points of interest for satellite earth observation according to the present invention.
FIG. 2 is a block diagram of a satellite-to-earth observation discrete point of interest cluster planning apparatus of the present invention.
Detailed Description
In order to make the above features and advantages of the present invention more comprehensible, the following description refers to embodiments accompanied with the present invention.
The invention aims to provide a satellite earth observation discrete interest point clustering planning method, which improves the observation efficiency of a large number of satellite earth discrete interest points.
The invention provides a satellite earth observation discrete interest point clustering planning method, which is shown in figure 1 and comprises the following steps.
(1) And inputting the position and the interestingness information of the discrete interest points.
Let the set of all ground points of interest be p=p i 1.ltoreq.i.ltoreq.n, n representing the total number of points in the collection. Wherein each point is denoted as P i ＝{x i ,y i ,w i I is more than or equal to 1 and less than or equal to n, i represents the serial number of the point, and x i Represents longitude, y i Represents latitude, w i Representing the degree of interest in that point. The set of clustering results is initialized to c= { }.
(2) And processing the interest points by adopting a sliding clustering method.
(2-1) selecting an arbitrary point P in the set P i Is the center of a circle.
(2-2) generating a circle C with r as the radius i Confirm to be at C i All points of interest in (1)
(2-3) according toCalculating and updating center position by the coordinate of the middle point and the interest value, and updating center coordinate P i ' asWherein n is C i Total number of midpoints, x j Longitude, y representing the jth point of interest j Represents the latitude, w of the jth point of interest j Indicating the interest level of the jth interest point, n indicating the interest point set +.>The number of points of interest; .
(2-4) at P i ' as the center of a circle, repeating the steps (2-2) and (2-3) until P is calculated twice consecutively i The cycle is stopped when the distance between' is less than the threshold d. At this time C i The circle center of (2) is the latest P i ′，C i Interest value of (2) isUpdating the set of clustering results c=c ≡c i 。
(2-5) C i All points in the map are removed from the interest point set P, and the set of the ground interest points is updatedRepeating steps (2-1) to (2-4) until P is empty.
(3) Planning the clustering result
(3-1) assume that the total scheduling time range is [ T ] S ,T E ]，T S 、T E Respectively representing the starting time and the ending time in the analysis time period; let it be assumed that the satellite set Sat k K is more than or equal to 1 and less than or equal to S, S represents the number of satellites, and the side swing angle beta of the satellites when the satellites move along a fixed orbit is within the range of-beta, beta]Variable, step size of change is Δβ, and is at [ T ] S ,T E ]The yaw angle β remains unchanged over time.
Let it be assumed that satellite Sat k Stripe set to ground g G is more than or equal to 1 and less than or equal to G, G is satellite Sat k Satellite Sat for the number of all possible target areas of the cluster result set C k Corresponding stripe g Is Ws kg And we kg Maximum storage capacity is E k Record e k Is satellite Sat k The storage capacity consumed per unit time.
The step (2-4) returns a set of cluster circles c= { C 1 ,C 2 ,...,C N N is the number of all circles in the clustering result C, and the radius of the circles is r. C corresponds to the interest level set v= { v 1 ,v 2 ,...,v N (v is shown in the figure) i Corresponding circle C i I is more than or equal to 1 and N is more than or equal to N.
(3-2) definition of decision variables
The objective function is expressed as a sum of the corresponding interestingness of the circles observed by the satellites and maximized for it:
s is the number of satellites and G is the satellite Sat k The number of all possible target areas within the region R, v i For corresponding circle C i Is a value of interest of (1).
(3-3) the above-described optimization procedure needs to satisfy the following constraints:
constraint 1: in the planned time interval, each circular area is required to be observed by the satellite at most once, namely:
constraint 2: the satellite operates in the whole dispatching time range, and the observation time of any strip must meet the imaging time requirement.
T S ≤ws kg ≤we kg ≤T E ,1≤k≤S,1≤g≤G (3-3)
Constraint 3: within the planned time interval, satellite Sat k Only one band at a roll angle can be selected in a single round.
Constraint 4: satellite storage capacity
(3-4) aiming at the objective function and the related constraint, the design utilizes a particle swarm algorithm (Particle Swarm Optimization, PSO) to optimize the problem, and the main flow is as follows:
(3-4-1) initial satellite and stripeChanging to set target area scheduling time T S ,T E ]And the visible time window of the selected satellite, particle swarm algorithm parameters, etc.
(3-4-2) inputting the number of satellites and the corresponding number of bands and related constraints as system variables into a calculation model, correcting the variables against the constraints (for example, each satellite can only select a corresponding band under a side sway angle under the same task), and calculating the maximum interest degree and Weight of the system as the current objective function value.
(3-4-3) determining the optimal combination pbest of the current satellite and the stripe according to the objective function, i.e. selecting the current optimal combination from the random combination scheme.
(3-4-4) determining an optimal combination of satellites and bands gbest selected from all pbest sets in the iteration. Gbest is taken as the global optimum for the population of particles, i.e. the optimal combination of selected satellites and bands.
And (3-4-5) judging whether the maximum iteration number (Max) is reached, if so, executing the step (3-4-6), and if not, returning to the step (3-4-2).
(3-4-6) outputting a global optimal solution gbest, namely an objective function Weight.
In summary, the method adjusts the center of the cluster according to the importance difference of each interest point, so that the area distribution of the discrete interest points is more clear, and by maximizing the corresponding interest sum corresponding to the clustering result, the calculation complexity of a planning algorithm is reduced, and the areas where the key interest points appear can be preferentially observed with high probability so as to reach higher overall observation benefit.
The invention also discloses a satellite earth observation discrete interest point clustering planning device which can be a computer device or can be arranged in the computer device. As shown in fig. 2, includes: an information acquisition module 201, a point of interest clustering module 202, a variable calculation module 203 and a cluster planning module 204.
An information acquisition module 201, configured to acquire information of interest points in a target area; wherein the information includes: longitude, latitude, and interest value;
the interest point clustering module 202 is configured to cluster the interest points based on the information, and obtain the interestingness of each category in the clustering result;
a variable calculation module 203 for calculating a satellite Sat k Acquiring the satellite Sat k Stripe in the target area kg And through the satellite Sat k Whether or not to observe the stripe kg Obtaining the value x of the decision variable kg ；
A cluster planning module 204 for determining the value x based on the interest level of each category kg Maximizing all satellites Sat k And observing the interest degree sum of the target area to obtain an interest point clustering planning result.
For details of the specific implementation process, beneficial effects, etc. of the device module, please refer to the description of the above method embodiment, and the details are not repeated here.
In an exemplary embodiment, there is also provided a computer device including a memory and a processor, the memory storing a computer program loaded and executed by the processor to implement the satellite earth observation discrete point of interest cluster planning method described above.
In an exemplary embodiment, a computer readable storage medium is also provided, having stored thereon a computer program which, when executed by a processor, implements a satellite earth observation discrete point of interest cluster planning method as described above.
In an exemplary embodiment, a computer program product is also provided which, when run on a computer device, causes the computer device to perform the satellite earth observation discrete point of interest cluster planning method as described above.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and are not limiting thereof; although the present application has been described in detail with reference to the above embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the above embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.
Claims (8)
1. A method for clustering and planning discrete points of interest of satellite earth observation, the method comprising:
acquiring information of interest points in a target area; wherein the information includes: longitude, latitude, and interest value;
clustering the interest points based on the information, and acquiring the interest degree of each category in the clustering result; the step of clustering the interest points based on the information to obtain the interest degree of each category in the clustering result comprises the following steps:
selecting any interest point from the current interest point set as a circle center;
generating a circle C by taking a set value as a radius i And is determined to be located in the circle C i All the interest points in the map are generated into an interest point set
According to the interest point setInformation of interest points in the circle C is updated i Until the distance between the circle center positions updated twice is smaller than a threshold value, obtaining a interest point subset based on the updated circle center positions;
acquiring the interest degree of the interest point subset based on the interest value of each interest point in the interest point subset;
deleting the interest point subset from the current interest point set, and judging whether the updated interest point set is an empty set or not;
returning to the current interest point set and selecting any interest point as a circle center under the condition that the updated interest point set is not an empty set;
outputting the interestingness of each interest point subset under the condition that the updated interest point set is an empty set;
according to satellite Sat k Acquiring the satellite Sat k Stripe in the target area g And through the satellite Sat k Whether or not to observe the stripe g Obtaining the strip script g The value x of the decision variable of (2) kg ；
Based on the interestingness of the categories and the value x of the decision variable kg Maximizing all satellites Sat k Observing the interest sum of the target area to obtain an interest point clustering planning result; wherein the value x based on the interestingness of each class and the decision variable kg Maximizing all satellites Sat k The interest degree sum when the target area is observed is used for obtaining an interest point clustering planning result, which comprises the following steps:
based on the interestingness and the value x kg Constructing an objective function to be optimized Wherein S represents the satellite Sat k G represents the number of the stripe stripes g Quantity v of (v) i Representing corresponding circle C i Is the interest level of (2);
setting constraint conditions of the objective function;
and optimizing the objective function to be optimized by using a particle swarm algorithm to obtain an interest point clustering planning result.
2. The method of claim 1, wherein the set of points of interest is based onLongitude and latitude of interest point in the circle C, updating the circle C i Is a center of a circle of (a), comprising:
based on the interest point setLongitude and interest value of interest point in the center of circle, and calculating longitude of new circle center positionWherein x is j Longitude, w representing the jth point of interest j An interest value representing the jth interest point, n representing the set of interest points +.>The number of points of interest;
based on the interest point setThe latitude and interest value of the interest point in the center of the circle, and the latitude of the new circle center position is calculatedWherein y is j Representing the latitude of the jth point of interest.
3. The method of claim 1, wherein said passing said satellite Sat k Whether or not to observe the stripe g Obtaining the value x of the decision variable kg Comprising:
at the satellite Sat k Observing the strip g In the case of (a), the value x of the decision variable kg ＝1；
At the satellite Sat k The strip is not observed g In the case of (a), the value x of the decision variable kg ＝0。
4. The method of claim 1, wherein the constraint of the objective function comprises:
the satellite Sat k Is a constraint on the observed quantity of (a); wherein the observed quantity constraint represents each of the following within a planned time intervalAt most, a circular area can only be covered by the satellite Sat k Observing for one time;
and, a step of, in the first embodiment,
the satellite Sat k Is a time constraint of imaging; wherein the imaging time constraint represents the satellite Sat k Run over the entire scheduling time range, any of the stripe strips g Must meet imaging time requirements;
and, a step of, in the first embodiment,
the satellite Sat k Is limited by the side swing angle; wherein the yaw angle constraint indicates that the satellite Sat is within a planned time interval k Only one strip under the side swing angle can be selected when the single clustering circle is passed;
and, a step of, in the first embodiment,
the satellite Sat k Is not limited by the storage capacity of the storage device.
5. The method of claim 1, wherein optimizing the objective function to be optimized using a particle swarm algorithm to obtain a point of interest cluster planning result comprises:
for the satellite Sat k With the strip g Initializing;
calculating the number of satellites, the number of corresponding target areas and related constraints as system variables, correcting the variables against the constraints, and taking the sum of the maximum interestingness of the calculated system as a current objective function value;
determining an optimal combination pbest of the current satellite and the strip according to the objective function;
selecting the optimal combination gbest of the satellite and the strip from the optimal combination pbest of all the iterative satellites and the strip;
judging whether the maximum iteration times are reached;
returning to the step of calculating the satellite number, the corresponding target area number and the related constraint as system variables under the condition that the maximum iteration number is not reached, and correcting the variables against the constraint to calculate the maximum weight sum of the system as the current objective function value;
and under the condition that the maximum iteration number is reached, taking the optimal combination gbest of the satellite and the strip as a ground observation planning result.
6. A satellite earth observation discrete point of interest cluster planning apparatus, the apparatus comprising:
the information acquisition module is used for acquiring information of interest points in the target area; wherein the information includes: longitude, latitude, and interest value;
the interest point clustering module is used for clustering the interest points based on the information and acquiring the interest degree of each category in the clustering result; the step of clustering the interest points based on the information to obtain the interest degree of each category in the clustering result comprises the following steps:
selecting any interest point from the current interest point set as a circle center;
generating a circle C by taking a set value as a radius i And is determined to be located in the circle C i All the interest points in the map are generated into an interest point set
According to the interest point setInformation of interest points in the circle C is updated i Until the distance between the circle center positions updated twice is smaller than a threshold value, obtaining a interest point subset based on the updated circle center positions;
acquiring the interest degree of the interest point subset based on the interest value of each interest point in the interest point subset;
deleting the interest point subset from the current interest point set, and judging whether the updated interest point set is an empty set or not;
returning to the current interest point set and selecting any interest point as a circle center under the condition that the updated interest point set is not an empty set;
outputting the interestingness of each interest point subset under the condition that the updated interest point set is an empty set;
the variable computing module is used for computing the variable according to the satellite Sat k Acquiring the satellite Sat k Stripe in the target area g And through the satellite Sat k Whether or not to observe the stripe g Obtaining the value x of the decision variable kg ；
A cluster planning module for based on the interestingness of each class and the value x kg Maximizing all satellites Sat k Observing the interest sum of the target area to obtain an interest point clustering planning result; wherein the value x based on the interestingness of each class and the decision variable kg Maximizing all satellites Sat k The interest degree sum when the target area is observed is used for obtaining an interest point clustering planning result, which comprises the following steps:
based on the interestingness and the value x kg Constructing an objective function to be optimized Wherein S represents the satellite Sat k G represents the number of the stripe stripes g Quantity v of (v) i Representing corresponding circle C i Is the interest level of (2);
setting constraint conditions of the objective function;
and optimizing the objective function to be optimized by using a particle swarm algorithm to obtain an interest point clustering planning result.
7. A storage medium having a computer program stored therein, wherein the computer program is arranged to perform the method of any of claims 1-5 when run.
8. An electronic device comprising a memory having stored therein a computer program and a processor arranged to run the computer program to perform the method of any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211348216.8A CN115909083B (en) | 2022-10-31 | 2022-10-31 | Satellite earth observation discrete interest point clustering planning method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211348216.8A CN115909083B (en) | 2022-10-31 | 2022-10-31 | Satellite earth observation discrete interest point clustering planning method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115909083A CN115909083A (en) | 2023-04-04 |
| CN115909083B true CN115909083B (en) | 2023-08-08 |
Family
ID=86492200
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211348216.8A Active CN115909083B (en) | 2022-10-31 | 2022-10-31 | Satellite earth observation discrete interest point clustering planning method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115909083B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110400002A (en) * | 2019-06-21 | 2019-11-01 | 中南大学 | A kind of more star imaging task planing methods |
| CN111897640A (en) * | 2020-07-31 | 2020-11-06 | 武汉大学 | Satellite imaging task planning method and system for regional mapping |
| CN112052269A (en) * | 2020-08-24 | 2020-12-08 | 腾讯科技（深圳）有限公司 | Position recommending method and device |
| CN112149911A (en) * | 2020-09-30 | 2020-12-29 | 武汉大学 | Hypersensitive short satellite same-orbit multipoint target in-motion imaging task planning method |
| CN113472420A (en) * | 2021-06-29 | 2021-10-01 | 大连大学 | Satellite network cache placement method based on regional user interest perception |
| CN114035913A (en) * | 2021-10-18 | 2022-02-11 | 南京航空航天大学 | Satellite multi-target repeated observation task planning method and terminal |
| CN114462681A (en) * | 2022-01-11 | 2022-05-10 | 武汉大学 | Task preprocessing method and system for hypersensitive short satellite multi-class target imaging integrated planning |
| CN115081225A (en) * | 2022-06-30 | 2022-09-20 | 上海交通大学 | Generalized remote sensing task planning method based on multi-order decision mechanism combination optimization |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101868819B1 (en) * | 2010-06-11 | 2018-06-19 | 스카이후크 와이어리스, 인크. | Methods of and Systems for Measuring Beacon Stability of Wireless Access Points |
-
2022
- 2022-10-31 CN CN202211348216.8A patent/CN115909083B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110400002A (en) * | 2019-06-21 | 2019-11-01 | 中南大学 | A kind of more star imaging task planing methods |
| CN111897640A (en) * | 2020-07-31 | 2020-11-06 | 武汉大学 | Satellite imaging task planning method and system for regional mapping |
| CN112052269A (en) * | 2020-08-24 | 2020-12-08 | 腾讯科技（深圳）有限公司 | Position recommending method and device |
| CN112149911A (en) * | 2020-09-30 | 2020-12-29 | 武汉大学 | Hypersensitive short satellite same-orbit multipoint target in-motion imaging task planning method |
| CN113472420A (en) * | 2021-06-29 | 2021-10-01 | 大连大学 | Satellite network cache placement method based on regional user interest perception |
| CN114035913A (en) * | 2021-10-18 | 2022-02-11 | 南京航空航天大学 | Satellite multi-target repeated observation task planning method and terminal |
| CN114462681A (en) * | 2022-01-11 | 2022-05-10 | 武汉大学 | Task preprocessing method and system for hypersensitive short satellite multi-class target imaging integrated planning |
| CN115081225A (en) * | 2022-06-30 | 2022-09-20 | 上海交通大学 | Generalized remote sensing task planning method based on multi-order decision mechanism combination optimization |
Non-Patent Citations (1)
| Title |
|---|
| 张耀元等.面向卫星多目标重复观测任务的分层聚类规划.《中国空间科学技术》.2022,第43卷(第1期),29-43. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115909083A (en) | 2023-04-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109409775B (en) | Satellite joint observation task planning method | |
| EP3323004B1 (en) | Computer-based representation of precipitation | |
| Luo et al. | Combining transfer learning and constrained long short-term memory for power generation forecasting of newly-constructed photovoltaic plants | |
| US11719858B2 (en) | Determination of location-specific weather information for agronomic decision support | |
| Wu et al. | Ensemble of metaheuristic and exact algorithm based on the divide-and-conquer framework for multisatellite observation scheduling | |
| Chou et al. | Recent advances in use of bio-inspired jellyfish search algorithm for solving optimization problems | |
| CN109039428B (en) | Relay satellite single-address antenna scheduling random search method based on conflict resolution | |
| CN112734239B (en) | Task planning method, device and medium based on task and resource capability attributes | |
| Sibtain et al. | A multistage hybrid model ICEEMDAN-SE-VMD-RDPG for a multivariate solar irradiance forecasting | |
| CN106845785A (en) | A kind of Multi-satellite TTC resource regulating method based on multiple objective function | |
| Li et al. | Sizing ramping reserve using probabilistic solar forecasts: A data-driven method | |
| CN112036598A (en) | Charging pile use information prediction method based on multi-information coupling | |
| Feng et al. | A method of distributed multi-satellite mission scheduling based on improved contract net protocol | |
| CN115909083B (en) | Satellite earth observation discrete interest point clustering planning method and device | |
| Vasanthkumar et al. | Improving energy consumption prediction for residential buildings using Modified Wild Horse Optimization with Deep Learning model | |
| CN111191941A (en) | Method for solving SEVM model problem based on artificial bee colony algorithm | |
| Deng et al. | Hybrid invasive weed optimization algorithm for parameter inversion problems | |
| CN116109036B (en) | Regional gridding multi-star observation planning method, device and equipment | |
| CN116089095B (en) | Deployment method for ReRAM neural network computing engine network | |
| CN115994176B (en) | Carbon emission analysis and report generation method based on big data and artificial intelligence | |
| CN117281016B (en) | Irrigation decision-making method, device and system of intercropping system based on unmanned aerial vehicle remote sensing | |
| Drzewiecki et al. | Multifractal parameters in prediction of land-use components on satellite images | |
| CN112598312B (en) | Electric vehicle charging scheduling method and device based on longicorn stigma search algorithm | |
| Li et al. | Multi-Satellite Mission Planning based on Multi-population Cooperative Parallel Evolutionary Algorithm | |
| Wu et al. | Research on Walnut (Juglans regia L.) Classification Based on Convolutional Neural Networks and Landsat-8 Remote Sensing Imagery |
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 | ||
| GR01 | Patent grant |