CN115344057B - Vegetation dense area route planning method, system, storage medium and electronic equipment - Google Patents
Vegetation dense area route planning method, system, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN115344057B CN115344057B CN202210765900.XA CN202210765900A CN115344057B CN 115344057 B CN115344057 B CN 115344057B CN 202210765900 A CN202210765900 A CN 202210765900A CN 115344057 B CN115344057 B CN 115344057B
- Authority
- CN
- China
- Prior art keywords
- vegetation
- route
- nodes
- coverage
- remote sensing
- 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
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/17—Terrestrial scenes taken from planes or by drones
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
Abstract
The invention discloses a vegetation dense area route planning method, a system, a storage medium and electronic equipment. And dividing the remote sensing image into a plurality of position nodes with the same size and shape according to the size and shape of the remote sensing image, and calculating the vegetation coverage of each position node according to the vegetation pixels and the non-vegetation pixels of the coverage area of the position nodes. And then, introducing vegetation coverage as an influence coefficient into the calculation of the transfer probability of the ant colony algorithm, and optimizing the state transfer rule of the unmanned aerial vehicle waypoints, thereby searching unmanned aerial vehicle route nodes in the vegetation dense area. And finally, planning the unmanned aerial vehicle flight route of the vegetation dense area based on the searched route nodes. Compared with the conventional route planning, the obtained route can autonomously avoid the ground environment with higher vegetation coverage in the area, and the probability of acquiring ground points is improved.
Description
Technical Field
The invention relates to the technical field of instruments for performing navigation computation, in particular to a method and a system for planning a route in a dense vegetation area, a storage medium and electronic equipment.
Background
The unmanned aerial vehicle three-dimensional laser scanning technology is an important means for acquiring accurate terrain information in ground disaster prevention and control. However, the current unmanned aerial vehicle track planning generally only considers factors such as operation time, plane and elevation precision, and the adverse effect of ground laser foot point sparseness of a vegetation coverage area on later fine terrain extraction is difficult to solve. Therefore, a technology for improving the number of laser pins collected by the unmanned aerial vehicle three-dimensional laser scanning system in the vegetation dense area to the ground is needed.
Disclosure of Invention
Aiming at the defects existing in the prior art, the invention provides a method, a system, a storage medium and electronic equipment for planning a route in a vegetation dense area. Can plan out a route that can improve unmanned aerial vehicle three-dimensional laser scanning system and acquire the probability of ground point to improve unmanned aerial vehicle three-dimensional laser scanning system and gather the laser foot point number to the ground in the intensive region of vegetation. The specific technical scheme is as follows:
in a first aspect, a method for planning a route in a dense vegetation area is provided, including:
acquiring a remote sensing image of a vegetation dense area;
classifying the remote sensing images, and determining vegetation pixels and non-vegetation pixels in the remote sensing images;
dividing the remote sensing image into a plurality of position nodes with the same size, and calculating vegetation coverage of each position node according to vegetation pixels and non-vegetation pixels of a coverage area of the position node;
based on the vegetation coverage, searching out route nodes from all position nodes by adopting an ant colony algorithm;
and planning unmanned aerial vehicle routes of the vegetation dense areas according to the searched route nodes.
With reference to the first aspect, in a first implementation manner of the first aspect, a random forest algorithm is used to classify the remote sensing image.
With reference to the first aspect, in a second implementation manner of the first aspect, when searching the route node, a transition probability between two location nodes is calculated according to the vegetation coverage.
With reference to the first aspect, in a third implementation manner of the first aspect, a least square curve fitting method is adopted to perform curve fitting on all route nodes, so as to obtain unmanned aerial vehicle routes in the vegetation dense area.
In a second aspect, a system for unmanned aerial vehicle route planning in a dense vegetation area is provided, comprising:
the acquisition module is configured to acquire a remote sensing image of the vegetation dense area;
the classifying module is configured to classify the remote sensing image and determine vegetation pixels and non-vegetation pixels in the remote sensing image;
the computing module is configured to divide the remote sensing image into a plurality of position nodes and compute the vegetation coverage of each position node according to the vegetation pixels and the non-vegetation pixels of the coverage area of the position nodes;
the searching module is configured to search out all route nodes from all position nodes by adopting an ant colony algorithm based on the vegetation coverage;
and the planning module is configured to plan unmanned aerial vehicle routes of the vegetation dense areas according to all route nodes.
With reference to the second aspect, in a first implementation manner of the second aspect, the classification module classifies the remote sensing image using a random forest algorithm.
With reference to the second aspect, in a second implementation manner of the second aspect, the searching module calculates a transition probability between two location nodes according to the vegetation coverage.
With reference to the second aspect, in a third implementation manner of the second aspect, the planning module performs curve fitting on all route nodes by adopting a least square curve fitting method to obtain an unmanned aerial vehicle route of the vegetation dense area.
In a third aspect, a storage medium is provided, in which a computer program is stored, where the computer program executes the vegetation dense area route planning method according to any one of the first aspect and the first to third aspects.
In a fourth aspect, there is provided an electronic device comprising:
one or more processors;
and a storage device configured to store one or more programs that, when executed by the one or more processors, cause the electronic device to implement the vegetation dense area route planning method of any one of the first aspect, the first through third aspects.
The beneficial effects are that: by adopting the vegetation dense area route planning method, the system, the storage medium and the electronic equipment, the vegetation coverage is extracted as the influence coefficient to be introduced into the transfer probability calculation of the ant colony algorithm based on the high-resolution remote sensing image, and the state transfer rule of the unmanned aerial vehicle waypoints is optimized, so that the unmanned aerial vehicle flight route of the vegetation dense area is obtained. Compared with the conventional route planning, the optimized route obtained by the method can autonomously avoid the ground environment with higher vegetation coverage in the area, and the probability of obtaining the ground point is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention, the drawings that are required to be used in the embodiments will be briefly described. Throughout the drawings, the elements or portions are not necessarily drawn to actual scale.
FIG. 1 is a flow chart of a method for planning a route in a dense vegetation area according to an embodiment of the present invention;
FIG. 2 is a flowchart of a remote sensing image classification method according to an embodiment of the present invention;
fig. 3 is a flowchart of an ant colony optimization algorithm according to an embodiment of the present invention;
FIG. 4 is a remote sensing image of a dense vegetation area acquired;
FIG. 5 is a schematic diagram of classification results of remote sensing images;
FIG. 6 is a sample division diagram;
FIG. 7 is a schematic illustration of a sample plant coverage calculation;
FIG. 8 is a schematic diagram of a location node constructed based on sample plant coverage points;
fig. 9 is a diagram showing a comparison of an optimized path obtained by the path planning method of the present invention and a normal path obtained by a normal ant colony algorithm;
FIG. 10 is a flight trajectory obtained by curve fitting using a least squares method;
fig. 11 is a system block diagram of a classification system according to an embodiment of the invention.
Detailed Description
Embodiments of the technical scheme of the present invention will be described in detail below with reference to the accompanying drawings. The following examples are only for more clearly illustrating the technical aspects of the present invention, and thus are merely examples, and are not intended to limit the scope of the present invention.
A flow chart of a method of vegetation dense area route planning as shown in fig. 1, the planning method comprising:
step 1, acquiring a remote sensing image of a vegetation dense area;
step 2, classifying the remote sensing images, and determining vegetation pixels and non-vegetation pixels in the remote sensing images;
step 3, dividing the remote sensing image into a plurality of position nodes with the same size, and calculating vegetation coverage of each position node according to vegetation pixels and non-vegetation pixels of a coverage area of the position node;
step 4, searching out route nodes from all position nodes by adopting an ant colony algorithm based on the vegetation coverage;
and 5, planning unmanned aerial vehicle routes of the vegetation dense areas according to the searched route nodes.
Specifically, first, a high-resolution remote sensing image of a region to be measured can be obtained through a satellite remote sensing image, and the collected remote sensing image is shown in fig. 4. And classifying each pixel in the acquired remote sensing image, and determining a vegetation pixel and a non-vegetation pixel in the remote sensing image. And dividing the remote sensing image into a plurality of position nodes with the same size and shape according to the size and shape of the remote sensing image, and calculating the vegetation coverage of each position node according to the vegetation pixels and the non-vegetation pixels of the coverage area of the position nodes. And then, introducing vegetation coverage as an influence coefficient into the calculation of the transfer probability of the ant colony algorithm, and optimizing the state transfer rule of the unmanned aerial vehicle waypoints, thereby searching unmanned aerial vehicle route nodes in the vegetation dense area. And finally, planning the unmanned aerial vehicle flight route of the vegetation dense area based on the searched route nodes. Compared with the conventional route planning, the optimized route obtained by the method can autonomously avoid the ground environment with higher vegetation coverage in the area, and the probability of obtaining the ground point is improved.
The classification of the remote sensing image in step 2 will be described in detail with reference to fig. 2.
In this embodiment, a random forest algorithm may be used to classify the remote sensing image, which specifically includes:
and 2-1, drawing a classification sample. And establishing classification samples in remote sensing image processing software according to the objects in the remote sensing image, wherein the classification samples are vegetation samples and non-vegetation samples respectively.
And 2-2, creating a sample data set. And creating a sample data set required by random forest classification based on the remote sensing image and the classified samples.
And 2-3, training a random forest classifier and storing a classification model. The sample data set is taken as classifier training data. Wherein, the RGB value of the pixel is the classification characteristic value of the pixel. The parameters of the random forest classifier are set as follows: the number of decision trees is 100, and the number of features to be considered when searching for the optimal segmentation is the square root of the number of features. And the training set and the test set respectively account for 90% and 10% of the sample data set.
And 2-4, inputting the obtained remote sensing image of the region to be detected into a trained random forest classification model, and storing the obtained classification result data in a grid data format, wherein the attribute value of the vegetation pixels is 255, and the attribute value of the non-vegetation pixels is 0.
By adopting the classification method, through multiple adjustment and repeated experiments on the samples, the accuracy of the classification training set and the accuracy of the test set respectively reach 95.38% and 95.05%, the classification accuracy can be used for integrally classifying the images, and the classification situation is shown in fig. 5:
the partitioning of the location nodes in step 3 will be described in detail below with reference to fig. 6 and 7.
In this embodiment, the remote sensing image may be divided into a plurality of rectangular samples with the same size and shape according to the size and shape of the remote sensing image, as shown in fig. 6. And taking each rectangular sample as a position node, as shown in fig. 7, calculating the area of a non-vegetation area and the area of a vegetation area in the rectangular sample coverage area according to the number of the vegetation pixels and the non-vegetation pixels in the rectangular sample coverage area, and calculating the vegetation coverage of each sample according to the area of the non-vegetation area and the area of the vegetation area in the rectangular sample coverage area. Because the rectangular sample contains more pixels, the vegetation coverage is adopted to set the position nodes, so that the data volume can be reduced, and the convergence time required by the ant colony algorithm is shortened. A location node is established on a per sample basis, as shown in fig. 8.
The search for the routing node in step 4 will be described in detail below in connection with fig. 3.
In this embodiment, an ant colony algorithm may be used to search out route nodes from all the location nodes, which specifically includes:
first, various parameters such as ant colony number, pheromone volatilization factor, pheromone constant, heuristic function factor and the like are initialized. Then, the ants are placed at different location nodes, and the next location node visited by each ant is determined until each ant has visited all the location nodes. In the ant access process, a roulette method can be adopted to select a next position node to be accessed, and the transition probability of the ants from the current position node to the next position node can be calculated according to the vegetation coverage, wherein the calculation formula of the transition probability is as follows:
the coverage is vegetation coverage, and coverage+1 is to avoid calculation errors when the coverage is 0.The transition probability of ant k from location node i to location node j at time t. τ ij (t) is the pheromone amount on the route (i, j) at the moment t; ηi j (t) is a heuristic function that represents the desired degree of transfer of ants from location node i to location node j.
τ is (t) is the pheromone amount from the position node i to the position node s at the time t; η (eta) is And (t) is the expected degree from the position node i to the position node s at the time t. Alpha is a pheromone heuristic factor, the larger the value of alpha is, the greater the possibility of the route passed by the ant before selecting is, otherwise, the searching range of the ant colony is reduced, the ant colony is easy to fall into local optimum, and the general value range is [1,4 ]]. Beta is a heuristic function factor, the larger the value of beta is, the easier the ant colony selects a local shorter route, the convergence rate of the algorithm is accelerated, and the values of [0,5 ] are generally taken]；allowedd k Is the set of forward route nodes allowed by ant k.
The calculation formula of the heuristic function is as follows:
d ij where is the distance, d, between position node i and position node j ij The smaller the transition probability pik j The larger (t). From the above calculation formula, it can be seen that the smaller the vegetation coverage, the greater the transition probability. Finally, ants can select a path with minimum vegetation coverage, namely the path which is least blocked by vegetation reaches a target point, and fly along the selected pathAnd the ground environment with higher vegetation coverage in the avoidance area is avoided, so that the probability of acquiring ground points is improved.
In this embodiment, the pheromone amount can be calculated using the following calculation formula:
τ ij (t+n)＝(1-ρ)*τ ij (t)+Δτ ij (t)，ρ∈(0，1)
wherein Deltaτ ij (t) is the sum of pheromones on the route (i, j) after all ants complete one traversal, ρ is the pheromone volatilization factor, m is the number of ants, τ ij (0) Has a value of c, c is a constant value, deltaτ ij (0) The value of (2) is 0.
In this embodiment, an ant colony period model is adopted as the pheromone updating policy in this embodiment, and the ant colony period model specifically includes:
where Q is the pheromone constant carried by each ant and Lk is the length of each ant search route.
In this embodiment, the results obtained by searching with the ant colony algorithm are discrete route nodes, which are not suitable for unmanned aerial vehicle flight. Therefore, the curve fitting can be performed by adopting a least square method, the continuous curves are used for fitting the searched route nodes, and the curve with the best fitting effect is the final vegetation dense area unmanned aerial vehicle route.
The two paths in fig. 9 are experimental results of track planning by adopting the classical ant colony algorithm and the ant colony optimization algorithm provided in this embodiment. After the route node search is completed, curve fitting is carried out according to the route node, and a route suitable for unmanned aerial vehicle flight is obtained. Fig. 10 is a fitted flight path. And respectively counting attribute values of the two path nodes, wherein the vegetation coverage in a sample corresponding to the common route construction node is 31.07%, and the vegetation coverage corresponding to the optimized route is 12.94%, and the same ratio is reduced by about 18%.
From the visual result of the route search, it can be seen that the ant colony optimization algorithm for the vegetation dense area of the embodiment can effectively solve the problem of track planning of ground observation of the unmanned aerial vehicle, and from the local details, the algorithm can effectively select the area with lower vegetation coverage, so that the unmanned aerial vehicle can acquire more ground information when finishing ground observation from the starting point to the end point.
A system block diagram of a vegetation dense area unmanned aerial vehicle en route planning system as shown in fig. 11, the planning system comprising:
the acquisition module is configured to acquire a remote sensing image of the vegetation dense area;
the classifying module is configured to classify the remote sensing image and determine vegetation pixels and non-vegetation pixels in the remote sensing image;
the computing module is configured to divide the remote sensing image into a plurality of position nodes and compute the vegetation coverage of each position node according to the vegetation pixels and the non-vegetation pixels of the coverage area of the position nodes;
the searching module is configured to search out all route nodes from all position nodes by adopting an ant colony algorithm based on the vegetation coverage;
and the planning module is configured to plan unmanned aerial vehicle routes of the vegetation dense areas according to all route nodes.
In particular, the acquisition module may acquire a high resolution remote sensing image of the area under test. The classification module classifies each pixel in the acquired remote sensing image and determines a vegetation pixel and a non-vegetation pixel in the remote sensing image. The computing module can divide the remote sensing image into a plurality of position nodes with the same size and shape according to the size and shape of the remote sensing image, and compute the vegetation coverage of each position node according to the vegetation pixels and the non-vegetation pixels of the coverage area of the position node. The searching module can introduce vegetation coverage as an influence coefficient into the transfer probability calculation of the ant colony algorithm, and optimize the state transfer rule of unmanned aerial vehicle waypoints, so that unmanned aerial vehicle route nodes in a vegetation dense area are searched. The planning module can plan the unmanned aerial vehicle flight route of the vegetation dense area based on the searched route nodes. Compared with the conventional route planning, the optimized route obtained by the method can autonomously avoid the ground environment with higher vegetation coverage in the area, and the probability of obtaining the ground point is improved.
In this embodiment, the classification module classifies the remote sensing image by using a random forest algorithm, and specifically, the classification module includes a model building unit and an image classification unit. The model building unit can build classification samples according to objects in the images by using remote sensing image processing software, and the classification samples are vegetation samples and non-vegetation samples respectively. And creating a sample data set required by random forest classification based on the remote sensing image and the classified samples. The model construction unit takes the sample data set as classifier training data to train the random forest model. The image classification unit can input the obtained remote sensing image of the region to be detected into a trained random forest classification model, and the obtained classification result data can be stored in a grid data format.
In this embodiment, the searching module calculates the transition probability between two location nodes according to the vegetation coverage.
Specifically, the searching module can search out the position node with the minimum vegetation coverage from all the position nodes by adopting an ant colony algorithm as a route node, so that the probability of acquiring ground points by the unmanned aerial vehicle three-dimensional laser scanning system can be improved, and the number of laser foot points acquired by the unmanned aerial vehicle three-dimensional laser scanning system in the vegetation dense area is improved.
The searching module comprises an initializing unit, a node searching unit and a pheromone updating unit. The initialization unit may initialize various parameters of the ant colony algorithm, such as ant colony number, pheromone volatilization factor, pheromone constant, heuristic function factor, etc.
The node searching unit may place the ants at different location nodes and determine the next location node visited by each ant until each ant has visited all the location nodes. In the ant access process, a roulette method can be adopted to select a next position node to be accessed, and the transition probability of the ants from the current position node to the next position node can be calculated according to the vegetation coverage, wherein the calculation formula of the transition probability is as follows:
the coverage is vegetation coverage, and coverage+1 is to avoid calculation errors when the coverage is 0.The transition probability of ant k from location node i to location node j at time t. τ ij (t) is the pheromone amount on the route (i, j) at the moment t; η (eta) ij (t) is a heuristic function that represents the desired degree of transfer of ants from location node i to location node j.
τ is (t) is the pheromone amount from the position node i to the position node s at the time t; η (eta) is And (t) is the expected degree from the position node i to the position node s at the time t. Alpha is a pheromone heuristic factor, the larger the value of alpha is, the greater the possibility of the route passed by the ant before selecting is, otherwise, the searching range of the ant colony is reduced, the ant colony is easy to fall into local optimum, and the general value range is [1,4 ]]. Beta is a heuristic function factor, the larger the value of beta is, the easier the ant colony selects a local shorter route, the convergence rate of the algorithm is accelerated, and the values of [0,5 ] are generally taken]；allowedd k Is the set of forward route nodes allowed by ant k.
The calculation formula of the heuristic function is as follows:
d ij where is the distance, d, between position node i and position node j ij The smaller the transition probabilityThe larger. From the above calculation formula, it can be seen that the smaller the vegetation coverage, the greater the transition probability. Finally, ants can select a path with minimum vegetation coverage, namely the path with minimum vegetation coverage reaches a target point, and fly along the selected path to avoid the ground environment with higher vegetation coverage in the area, so that the probability of acquiring the ground point is improved.
The pheromone updating unit may calculate using the following calculation formula:
τ ij (t+n)＝(1-ρ)*τij(t)+Δτ ij (t)，p∈(0，1)
wherein Deltaτi j (t) is the sum of pheromones on the route (i, j) after all ants complete one traversal, ρ is the pheromone volatilization factor, m is the number of ants, τ ij (0) Has a value of c, c is a constant value, deltaτ ij (0) The value of (2) is 0. And adopts an ant colony period model as a pheromone updating strategy of the embodiment, wherein the ant colony period model is specifically as follows:
where Q is the pheromone constant carried by each ant and Lk is the length of each ant search route.
In this embodiment, the planning module performs curve fitting on all route nodes by using a least square curve fitting method, so as to obtain the unmanned aerial vehicle route in the vegetation dense area. The results obtained by searching by the searching module are discrete route nodes respectively, and are not suitable for unmanned aerial vehicle flight. Therefore, the planning module can adopt a least square method to carry out curve fitting, continuous curves are used for fitting the route nodes searched by the searching module, and the curve with the best fitting effect is the final vegetation dense area unmanned aerial vehicle route.
A storage medium storing a computer program for executing the vegetation dense area route planning method described above.
An electronic device, comprising:
one or more processors;
and the storage device is used for storing one or more programs, and when the one or more programs are executed by the one or more processors, the electronic equipment realizes the vegetation dense area route planning method.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention, and are intended to be included within the scope of the appended claims and description.
Claims (10)
1. The method for planning the route of the vegetation dense area is characterized by comprising the following steps:
acquiring a remote sensing image of a vegetation dense area;
classifying the remote sensing images, and determining vegetation pixels and non-vegetation pixels in the remote sensing images;
dividing the remote sensing image into a plurality of same position nodes, and calculating vegetation coverage of each position node according to vegetation pixels and non-vegetation pixels of a coverage area of the position node;
introducing vegetation coverage as an influence coefficient into the calculation of transition probability of an ant colony algorithm, and searching out route nodes from all position nodes by adopting the ant colony algorithm, wherein the calculation formula of the transition probability is as follows:
wherein coverage is the vegetation coverage,the transition probability of ant k from the position node i to the position node j at the time t; τ ij (t) is the pheromone amount on the route (i, j) at the moment t; η (eta) ij (t) is the expected degree of ant transfer from location node i to location node j; allowedd k Is the set of ant k allowed forward route nodes, beta is heuristic function factor, alpha is pheromone heuristic factor, eta is (t) is the expected degree of position node i to position node s at time t, τ is (t) is the pheromone amount from the position node i to the position node s at the time t;
and planning unmanned aerial vehicle routes of the vegetation dense areas according to the searched route nodes.
2. The vegetation dense area route planning method of claim 1 wherein the remote sensing images are classified using a random forest algorithm.
3. The vegetation dense area route planning method of claim 1 wherein a transition probability between two location nodes is calculated from the vegetation coverage when searching for the route nodes.
4. The method for planning a course of a vegetation dense area according to claim 1, wherein a least squares curve fitting method is adopted to perform curve fitting on all course nodes, so as to obtain an unmanned aerial vehicle course of the vegetation dense area.
5. Unmanned aerial vehicle route planning system in vegetation dense area, characterized by comprising:
the acquisition module is configured to acquire a remote sensing image of the vegetation dense area;
the classifying module is configured to classify the remote sensing image and determine vegetation pixels and non-vegetation pixels in the remote sensing image;
the computing module is configured to divide the remote sensing image into a plurality of position nodes and compute the vegetation coverage of each position node according to the vegetation pixels and the non-vegetation pixels of the coverage area of the position nodes;
the searching module is configured to introduce vegetation coverage as an influence coefficient into calculation of transition probability of an ant colony algorithm, and search route nodes from all position nodes by adopting the ant colony algorithm, wherein the calculation formula of the transition probability is as follows:
wherein coverage is the vegetation coverage,the transition probability of ant k from the position node i to the position node j at the time t; τ ij (t) is the pheromone amount on the route (i, j) at the moment t; η (eta) ij (t) is the expected degree of ant transfer from location node i to location node j; allowedd k Is the set of ant k allowed forward route nodes, beta is heuristic function factor, alpha is pheromone heuristic factor, eta is (t) is the expected degree of position node i to position node s at time t, τ is (t) is the pheromone amount from the position node i to the position node s at the time t;
and the planning module is configured to plan unmanned aerial vehicle routes of the vegetation dense areas according to all route nodes.
6. The vegetation dense area unmanned aerial vehicle route planning system of claim 5, wherein the classification module classifies the remote sensing images using a random forest algorithm.
7. The vegetation dense area unmanned aerial vehicle routing system of claim 5, wherein the search module calculates a transition probability between two location nodes based on the vegetation coverage.
8. The unmanned aerial vehicle route planning system of claim 5, wherein the planning module performs curve fitting on all route nodes by using a least squares curve fitting method to obtain the unmanned aerial vehicle route of the vegetation dense area.
9. A storage medium storing a computer program for executing the vegetation dense area route planning method according to any one of claims 1 to 4.
10. An electronic device, comprising:
one or more processors;
storage means for storing one or more programs that, when executed by the one or more processors, cause an electronic device to implement the vegetation dense area route planning method of any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210765900.XA CN115344057B (en) | 2022-06-30 | 2022-06-30 | Vegetation dense area route planning method, system, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210765900.XA CN115344057B (en) | 2022-06-30 | 2022-06-30 | Vegetation dense area route planning method, system, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115344057A CN115344057A (en) | 2022-11-15 |
| CN115344057B true CN115344057B (en) | 2023-09-19 |
Family
ID=83948380
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210765900.XA Active CN115344057B (en) | 2022-06-30 | 2022-06-30 | Vegetation dense area route planning method, system, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115344057B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101160103A (en) * | 2005-01-18 | 2008-04-09 | MSq有限公司 | System and method for treating biological tissue with a plasma gas discharge |
| CN102012528A (en) * | 2010-11-23 | 2011-04-13 | 北京理工大学 | Hyperspectral remote sensing oil-gas exploration method for vegetation sparse area |
| CN106650991A (en) * | 2016-09-27 | 2017-05-10 | 中国矿业大学(北京) | Path planning based on analog annealing ant colony algorithm |
| CN107219860A (en) * | 2017-07-31 | 2017-09-29 | 内蒙古智牧溯源技术开发有限公司 | A kind of unmanned plane rang management system and method |
| CN109240304A (en) * | 2018-10-15 | 2019-01-18 | 南京林业大学 | A kind of precision planting system and method |
| CN114219966A (en) * | 2021-11-11 | 2022-03-22 | 中国科学院地理科学与资源研究所 | Method for extracting plant coverage and computer readable storage medium |
| WO2022077954A1 (en) * | 2020-10-14 | 2022-04-21 | 国防科技大学 | Unmanned aerial vehicle path planning method based on two charging modes |
-
2022
- 2022-06-30 CN CN202210765900.XA patent/CN115344057B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101160103A (en) * | 2005-01-18 | 2008-04-09 | MSq有限公司 | System and method for treating biological tissue with a plasma gas discharge |
| CN102012528A (en) * | 2010-11-23 | 2011-04-13 | 北京理工大学 | Hyperspectral remote sensing oil-gas exploration method for vegetation sparse area |
| CN106650991A (en) * | 2016-09-27 | 2017-05-10 | 中国矿业大学(北京) | Path planning based on analog annealing ant colony algorithm |
| CN107219860A (en) * | 2017-07-31 | 2017-09-29 | 内蒙古智牧溯源技术开发有限公司 | A kind of unmanned plane rang management system and method |
| CN109240304A (en) * | 2018-10-15 | 2019-01-18 | 南京林业大学 | A kind of precision planting system and method |
| WO2022077954A1 (en) * | 2020-10-14 | 2022-04-21 | 国防科技大学 | Unmanned aerial vehicle path planning method based on two charging modes |
| CN114219966A (en) * | 2021-11-11 | 2022-03-22 | 中国科学院地理科学与资源研究所 | Method for extracting plant coverage and computer readable storage medium |
Non-Patent Citations (4)
| Title |
|---|
| 森林防火机器人轨迹寻踪技术研究;布升强;梅淼;李琼琼;杨家富;王大明;;森林工程(第03期);全文 * |
| 植保无人机主要性能指标测评方法的分析与思考;徐小杰;陈盛德;周志艳;兰玉彬;罗锡文;;农机化研究(第12期);全文 * |
| 植保无人机航空喷施作业有效喷幅的评定与试验;陈盛德;兰玉彬;李继宇;徐小杰;王志国;彭斌;;农业工程学报(第07期);全文 * |
| 陈盛德 ; 兰玉彬 ; 李继宇 ; 徐小杰 ; 王志国 ; 彭斌 ; .植保无人机航空喷施作业有效喷幅的评定与试验.农业工程学报.2017,(第07期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115344057A (en) | 2022-11-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107690840B (en) | Unmanned plane vision auxiliary navigation method and system | |
| US11302105B2 (en) | Grid map obstacle detection method fusing probability and height information | |
| CN111666855B (en) | Animal three-dimensional parameter extraction method and system based on unmanned aerial vehicle and electronic equipment | |
| Emmi et al. | A hybrid representation of the environment to improve autonomous navigation of mobile robots in agriculture | |
| Noordermeer et al. | Predicting and mapping site index in operational forest inventories using bitemporal airborne laser scanner data | |
| CN108428220A (en) | Satellite sequence remote sensing image sea island reef region automatic geometric correction method | |
| Vivaldini et al. | UAV route planning for active disease classification | |
| CN114119920A (en) | Three-dimensional point cloud map construction method and system | |
| EP3842836A1 (en) | Method, apparatus and storage medium for positioning object | |
| Aguiar et al. | Localization and mapping on agriculture based on point-feature extraction and semiplanes segmentation from 3D LiDAR data | |
| CN113516664A (en) | Visual SLAM method based on semantic segmentation dynamic points | |
| CN113096181B (en) | Method and device for determining equipment pose, storage medium and electronic device | |
| CN111046756A (en) | Convolutional neural network detection method for high-resolution remote sensing image target scale features | |
| JP5771866B2 (en) | Area survey support system, area survey support method, and area survey support device | |
| Williams et al. | Three-dimensional segmentation of trees through a flexible multi-class graph cut algorithm (MCGC) | |
| CN115344057B (en) | Vegetation dense area route planning method, system, storage medium and electronic equipment | |
| Bouman et al. | Adaptive coverage path planning for efficient exploration of unknown environments | |
| Wang et al. | Robust exploration with multiple hypothesis data association | |
| CN116739739A (en) | Loan amount evaluation method and device, electronic equipment and storage medium | |
| CN115469662B (en) | Environment exploration method, device and application | |
| Leung et al. | Evaluating set measurement likelihoods in random-finite-set slam | |
| CN116661479A (en) | Building inspection path planning method, equipment and readable storage medium | |
| CN115909027A (en) | Situation estimation method and device | |
| CN115619953A (en) | Rugged terrain-oriented mobile robot terrain mapping method and system | |
| CN115019216A (en) | Real-time ground object detection and positioning counting method, system and computer |
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 |