CN113190031B - Forest fire automatic photographing and tracking method, device and system based on unmanned aerial vehicle - Google Patents
Forest fire automatic photographing and tracking method, device and system based on unmanned aerial vehicle Download PDFInfo
- Publication number
- CN113190031B CN113190031B CN202110484192.8A CN202110484192A CN113190031B CN 113190031 B CN113190031 B CN 113190031B CN 202110484192 A CN202110484192 A CN 202110484192A CN 113190031 B CN113190031 B CN 113190031B
- Authority
- CN
- China
- Prior art keywords
- forest fire
- dimensional
- fire area
- point cloud
- convex hull
- 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
Images
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
- G05D1/08—Control of attitude, i.e. control of roll, pitch, or yaw
- G05D1/0808—Control of attitude, i.e. control of roll, pitch, or yaw specially adapted for aircraft
-
- 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
- G05D1/106—Change initiated in response to external conditions, e.g. avoidance of elevated terrain or of no-fly zones
-
- 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
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/10—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture
- Y02A40/28—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture specially adapted for farming
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the technical field of route planning, in particular to an automatic photographing and tracking method, device and system for forest fires based on an unmanned aerial vehicle. According to the automatic photographing and tracking method for the forest fire based on the unmanned aerial vehicle, the position coordinates of the forest fire area are received, and a convex hull of the forest fire area is generated according to the original geographic information point cloud; generating a two-dimensional air route of the unmanned aerial vehicle according to the convex hull of the forest fire area; generating an unmanned aerial vehicle three-dimensional route according to the original geographic information point cloud and the unmanned aerial vehicle two-dimensional route; and dynamically monitoring whether the three-dimensional air route of the unmanned aerial vehicle threatens forest fire, if so, updating the position coordinates of the forest fire area to regenerate the three-dimensional air route of the unmanned aerial vehicle, and realizing monitoring and positioning of new boundary coordinates of the forest fire area and updating to obtain the current optimized air route while planning the air route.
Description
Technical Field
The invention relates to the technical field of route planning, in particular to an automatic photographing and tracking method, device and system for forest fires based on an unmanned aerial vehicle.
Background
At present, forest fire monitoring means mainly comprise: monitoring means such as satellite remote sensing, tower observation, ground patrol, airplane patrol, unmanned aerial vehicle technology and the like. The satellite remote sensing technology is easily affected by the orbit period and weather, the real-time performance is poor, and the resolution ratio is low; although the tower lookout technology is good in real-time performance, the range is limited, networking equipment needs to be configured, the cost is high, the tower lookout technology is easily influenced by the terrain, and blind spots exist; the ground inspection efficiency is low, the sight line is easy to be shielded, and the monitoring range is limited; the airplane patrol technology has good real-time performance and adaptability, but the cost for maintaining and using equipment is higher, and the large-scale and normalized use is difficult; the unmanned aerial vehicle technology has the advantages of good real-time performance, good stability, higher resolution, faster data transmission, low cost and the like.
However, the existing unmanned aerial vehicle can only manually set a flight route for forest fire monitoring, and can only visually estimate the position of the forest fire by manpower, does not have an exact value, and cannot dynamically plan the flight route according to the forest fire in real time to carry out fine routing inspection on the forest fire.
Disclosure of Invention
In view of this, the present application provides an automatic forest fire photographing and tracking method, apparatus, and system based on an unmanned aerial vehicle, which can solve or partially solve the above existing problems.
In order to solve the technical problems, the technical scheme provided by the invention is an automatic photographing and tracking method for forest fires based on an unmanned aerial vehicle, which comprises the following steps:
s11: receiving position coordinates of the forest fire area, and generating a forest fire area convex hull according to the original geographic information point cloud;
s12: generating a two-dimensional route of the unmanned aerial vehicle according to the convex hull of the forest fire area;
s13: generating an unmanned aerial vehicle three-dimensional route according to the original geographic information point cloud and the unmanned aerial vehicle two-dimensional route;
s14: and dynamically monitoring whether the three-dimensional air route of the unmanned aerial vehicle threatens forest fire, and if so, updating the position coordinates of the forest fire area to regenerate the three-dimensional air route of the unmanned aerial vehicle.
Preferably, the S11 includes:
s111: receiving position coordinates of the forest fire area, and generating a two-dimensional forest fire area point cloud according to the original geographic information point cloud;
s112: diluting the two-dimensional forest fire area point cloud to obtain a diluted two-dimensional forest fire area point cloud;
s113: and calculating a convex hull of the diluted two-dimensional forest fire area point cloud through an Andre algorithm based on a horizontal sequence in the convex hull algorithm to obtain the two-dimensional forest fire area point cloud convex hull.
Preferably, the step of S111 includes:
s1111: respectively setting limiting ranges of an X axis and a Y axis in the direct filtering according to the position coordinates of the forest fire area to cut the original geographic information point cloud to obtain the forest fire area point cloud;
s1112: projecting the forest fire area point cloud to a two-dimensional plane to obtain a two-dimensional forest fire area point cloud;
preferably, the step of S112 includes:
s1121: according to parameter information of the two-dimensional forest fire area point cloud, a three-dimensional voxel grid is created through a Voxelgrid filter;
s1122: and representing all points in the three-dimensional voxel grid through the gravity center point in the three-dimensional voxel grid to obtain the diluted two-dimensional forest fire area point cloud.
Preferably, the step of S113 includes:
s1131: sequencing the diluted two-dimensional forest fire area point clouds from small to large according to the coordinate value X, and obtaining a vertex sequence p 1 ,p 2 ,...,p n ，
S1133: p is to be 1 And p 2 Put into a point cloud convex hull of a two-dimensional forest fire area from p 3 Starting, when the current point is in the anticlockwise direction of the two-dimensional forest fire area point cloud convex hull, continuing to put the current point into the two-dimensional forest fire area point cloud convex hull, otherwise, sequentially deleting the points which are recently added into the two-dimensional forest fire area point cloud convex hull until a new point is in the anticlockwise direction, repeating the process until the rightmost p is touched n Calculating a lower convex hull of the point cloud convex hull of the two-dimensional forest fire area;
s1134: p is to be n And p n-1 Put into a point cloud convex hull of a two-dimensional forest fire area from p n-2 Starting, when the current point is in the anticlockwise direction of the two-dimensional forest fire area point cloud convex hull, continuing to put the current point into the two-dimensional forest fire area point cloud convex hull, otherwise, sequentially deleting the points which are recently added into the two-dimensional forest fire area point cloud convex hull until a new point is in the anticlockwise direction, repeating the process until the leftmost p is touched 1 Solving an upper convex hull of the point cloud convex hull of the two-dimensional forest fire area;
s1135: and sequentially judging whether points on the two-dimensional forest fire area point cloud convex hull are all on the convex hull, and if not, deleting the points.
Preferably, the step of S12 includes:
s121: calculating the gravity center of the point cloud convex hull of the two-dimensional forest fire area according to the two-dimensional point cloud on the boundary of the point cloud convex hull of the two-dimensional forest fire area;
s122: and calculating the two-dimensional air route of the unmanned aerial vehicle by an algorithm of scaling up irregular polygons in equal proportion according to the coordinates of each vertex of the two-dimensional forest fire area point cloud convex hull, the gravity center of the two-dimensional forest fire area point cloud convex hull and the preset safe flying distance.
Preferably, the step S13 is:
s131: the method comprises the steps that original geographical information point clouds corresponding to forest fire area convex hulls one by one are used for obtaining original altitude data, and preset altitude data are added to be used as a course altitude;
s132: judging whether the distance between vertexes of the two-dimensional route of the unmanned aerial vehicle is larger than a preset distance or not, if so, judging the actual altitude of the point at every preset distance, calculating whether the altitude difference between the route altitude of the unmanned aerial vehicle and the actual altitude is larger than a preset altitude difference value or not, and if not, resetting the route altitude as the actual altitude plus preset altitude data;
s133: and adding the altitude of the air route to the two-dimensional air route of the unmanned aerial vehicle to obtain the three-dimensional air route of the unmanned aerial vehicle.
Preferably, the step of S14 includes:
s141: taking a picture of forest fire at a preset monitoring point on a three-dimensional route of the unmanned aerial vehicle to obtain a first image, keeping current camera parameters unchanged, moving a preset distance from the monitoring point to the gravity center direction of a point cloud convex hull of a two-dimensional forest fire area, and taking a picture to obtain a second image;
s142: processing the first image and the second image through an opencv image processing library to screen out forest fire areas;
s143: calculating pixels occupied by the heights of the forest fire areas in the first image and the second image, and calculating the distance between the unmanned aerial vehicle in the forest fire area and the boundary of the current forest fire area through a monocular vision distance measurement algorithm;
s144: calculating longitude and latitude coordinates of a forest fire area through longitude and latitude coordinates of unmanned aerial vehicle photographing and the head orientation and pitch angle of the unmanned aerial vehicle photographing acquired from an unmanned aerial vehicle built-in system;
s145: and judging whether the distance from the longitude and latitude coordinates of the forest fire area to the three-dimensional route is greater than a preset safety distance, if so, adding the longitude and latitude coordinates of the forest fire area into the coordinates of the forest fire area without action, and if not, adding the longitude and latitude coordinates of the forest fire area into the coordinates of the forest fire area to regenerate the three-dimensional route of the unmanned aerial vehicle.
The invention also provides an automatic forest fire photographing and tracking device based on the unmanned aerial vehicle, which comprises:
the forest fire convex hull generating module is used for receiving the position coordinates of the forest fire area and generating a forest fire area convex hull according to the original geographic information point cloud;
the two-dimensional route generation module is used for generating the two-dimensional route of the unmanned aerial vehicle according to the convex hull of the forest fire area;
the three-dimensional route generation module is used for generating an unmanned aerial vehicle three-dimensional route according to the original geographic information point cloud and the unmanned aerial vehicle two-dimensional route;
and the forest fire dynamic monitoring module is used for dynamically monitoring whether the three-dimensional air line of the unmanned aerial vehicle threatens forest fire, and if yes, updating the position coordinates of the forest fire area to regenerate the three-dimensional air line of the unmanned aerial vehicle.
Preferably, the forest fire convex hull generating module includes:
the two-dimensional forest fire point cloud generating unit is used for receiving the position coordinates of the forest fire area and generating a two-dimensional forest fire area point cloud according to the original geographic information point cloud;
the two-dimensional forest fire point cloud diluting unit is used for diluting the two-dimensional forest fire area point cloud to obtain a diluted two-dimensional forest fire area point cloud;
and the two-dimensional forest fire convex hull calculating unit is used for calculating the convex hull of the diluted two-dimensional forest fire area point cloud through an Andre algorithm based on a horizontal sequence in the convex hull algorithm to obtain the two-dimensional forest fire area point cloud convex hull.
Preferably, the two-dimensional route generation module includes:
the forest fire convex hull gravity center calculating unit is used for calculating the gravity center of the two-dimensional forest fire area point cloud convex hull according to the two-dimensional point cloud on the boundary of the two-dimensional forest fire area point cloud convex hull;
and the unmanned aerial vehicle two-dimensional route calculation unit is used for calculating the two-dimensional route of the unmanned aerial vehicle through an algorithm for amplifying irregular polygons in equal proportion according to the coordinates of each vertex of the two-dimensional forest fire area point cloud convex hull, the gravity center of the two-dimensional forest fire area point cloud convex hull and the preset safe flying distance.
Preferably, the three-dimensional route generation module includes:
the system comprises a route altitude acquisition unit, a route searching unit and a route searching unit, wherein the route altitude acquisition unit is used for acquiring original altitude data by mapping the forest fire area convex hulls to original geographic information point clouds one by one, and adding preset altitude data as a route altitude;
the actual altitude calculation unit is used for judging whether the distance between vertexes of the two-dimensional air route of the unmanned aerial vehicle is larger than a preset distance or not, if so, judging the actual altitude of the point at each preset distance, calculating whether the altitude difference between the air route altitude of the unmanned aerial vehicle and the actual altitude is larger than a preset altitude difference or not, and if not, resetting the air route altitude to be the actual altitude plus preset altitude data;
and the unmanned aerial vehicle three-dimensional route generation unit is used for adding the route altitude to the unmanned aerial vehicle two-dimensional route to obtain the unmanned aerial vehicle three-dimensional route.
Preferably, the forest fire dynamic monitoring module includes:
the system comprises a monitoring image acquisition unit, a first image acquisition unit and a second image acquisition unit, wherein the monitoring image acquisition unit is used for photographing forest fires at a preset monitoring point on a three-dimensional air route of the unmanned aerial vehicle to obtain a first image, storing the current camera parameters unchanged, and moving a preset distance from the monitoring point to the gravity center direction of a point cloud convex hull of a two-dimensional forest fire area to photograph to obtain a second image;
the forest fire area screening unit is used for processing the first image and the second image through the opencv image processing library and screening out a forest fire area;
the forest fire distance calculating unit is used for calculating pixels occupied by heights of the forest fire areas in the first image and the second image, and calculating the distance between the unmanned aerial vehicle in the forest fire areas and the boundary of the current forest fire areas through a monocular vision distance measuring algorithm;
the forest fire coordinate calculation unit is used for calculating the longitude and latitude coordinates of a forest fire area through the longitude and latitude coordinates of the unmanned aerial vehicle photographing and the head orientation and the pitch angle of the unmanned aerial vehicle photographing, which are acquired from the unmanned aerial vehicle built-in system;
and the forest fire safety judgment unit is used for judging whether the distance from the longitude and latitude coordinates of the forest fire area to the three-dimensional route is greater than a preset safety distance, if so, adding the longitude and latitude coordinates of the forest fire area into the forest fire area coordinates without action, and if not, adding the longitude and latitude coordinates of the forest fire area into the forest fire area coordinates to regenerate the three-dimensional route of the unmanned aerial vehicle.
The invention also provides an automatic forest fire photographing and tracking system based on the unmanned aerial vehicle, which comprises the following components:
a memory for storing a computer program;
and the processor is used for executing the computer program to realize the steps of the automatic photographing and tracking method for the forest fire based on the unmanned aerial vehicle.
The invention also provides a readable storage medium, which stores a computer program, and the computer program is executed by a processor to realize the steps of the forest fire automatic photographing and tracking method based on the unmanned aerial vehicle.
Compared with the prior art, the beneficial effects of the method are detailed as follows: according to the automatic photographing and tracking method for the forest fire based on the unmanned aerial vehicle, the position coordinates of the forest fire area are received, and a convex hull of the forest fire area is generated according to the original geographic information point cloud; generating a two-dimensional route of the unmanned aerial vehicle according to the convex hull of the forest fire area; generating an unmanned aerial vehicle three-dimensional route according to the original geographic information point cloud and the unmanned aerial vehicle two-dimensional route; and dynamically monitoring whether the three-dimensional air route of the unmanned aerial vehicle threatens forest fire or not, if so, updating the position coordinates of the forest fire area to regenerate the three-dimensional air route of the unmanned aerial vehicle, and realizing monitoring and positioning of new boundary coordinates of the forest fire area and updating to obtain the current optimized air route while planning the air route.
Drawings
In order to illustrate the embodiments of the present invention more clearly, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings can be obtained by those skilled in the art without inventive effort.
Fig. 1 is a schematic flow chart of a forest fire automatic photographing tracking method based on an unmanned aerial vehicle according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a method for generating a convex hull of a forest fire area according to an embodiment of the present invention;
fig. 3 is a schematic flow chart of a method for planning a two-dimensional route of an unmanned aerial vehicle according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a method for calculating a two-dimensional route of an unmanned aerial vehicle according to an embodiment of the present invention;
fig. 5 is a schematic flow chart of a method for planning a three-dimensional route of an unmanned aerial vehicle according to an embodiment of the present invention;
fig. 6 is a forest fire automatic photographing tracking device based on an unmanned aerial vehicle according to an embodiment of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present invention without any creative work belong to the protection scope of the present invention.
In order to make the technical solutions of the present invention better understood by those skilled in the art, the present invention will be further described in detail with reference to the accompanying drawings and specific embodiments.
As shown in fig. 1, an embodiment of the present invention provides an automatic forest fire photographing and tracking method based on an unmanned aerial vehicle, including:
s11: receiving position coordinates of the forest fire area, and generating a forest fire area convex hull according to the original geographic information point cloud;
s12: generating a two-dimensional route of the unmanned aerial vehicle according to the convex hull of the forest fire area;
s13: generating an unmanned aerial vehicle three-dimensional route according to the original geographic information point cloud and the unmanned aerial vehicle two-dimensional route;
s14: and dynamically monitoring whether the three-dimensional air route of the unmanned aerial vehicle threatens forest fire, and if so, updating the position coordinates of the forest fire area to regenerate the three-dimensional air route of the unmanned aerial vehicle.
As shown in fig. 2, S11 includes:
s111: receiving position coordinates of the forest fire area, and generating a two-dimensional forest fire area point cloud according to the original geographic information point cloud;
s112: diluting the two-dimensional forest fire area point cloud to obtain a diluted two-dimensional forest fire area point cloud;
s113: and calculating a convex hull of the diluted two-dimensional forest fire area point cloud through an Andre algorithm based on a horizontal sequence in the convex hull algorithm to obtain the two-dimensional forest fire area point cloud convex hull.
Specifically, in S11, a laser radar is used to obtain point cloud information, i.e., a las file, of the area; software acquires longitude and latitude coordinates of boundary points in the forest fire approximate range; and mapping the acquired position information of the forest fire area into point cloud data, obtaining the point cloud data of the forest fire area by cutting the original point cloud file, and diluting the point cloud data of the forest fire area.
The step S111 includes:
s1111: respectively setting limiting ranges of an X axis and a Y axis in the direct filtering according to the position coordinates of the forest fire area to cut the original geographic information point cloud to obtain the forest fire area point cloud;
s1112: and projecting the forest fire area point cloud to a two-dimensional plane to obtain a two-dimensional forest fire area point cloud.
Specifically, (1) filtering the original point cloud data by the software in a direct filtering mode on X and Y coordinate axes respectively, and selecting the point cloud in the reserved range to cut out the point cloud of the forest fire area. (2) When the software processes the point cloud of the forest fire area, the elevation information is temporarily ignored, the position information of the forest fire area is projected to a two-dimensional horizontal plane, and two-dimensional horizontal point cloud data of the forest fire area are obtained.
The step S112 includes:
s1121: according to parameter information of the two-dimensional forest fire area point cloud, a three-dimensional voxel grid is created through a Voxelgrid filter;
s1122: and representing all points in the three-dimensional voxel grid through a gravity center point in the three-dimensional voxel grid to obtain a diluted two-dimensional forest fire area point cloud.
Specifically, in order to reduce the calculation amount, the software dilutes the forest fire area point cloud through point cloud filtering. Voxel filtering in the point cloud filtering is adopted. The specific treatment steps are as follows: (1) The size of a single three-dimensional voxel grid (which can be thought as a tiny three-dimensional cube) is set through parameter information in a point cloud data las file and actual conditions; (2) All points in the voxel grid are represented by the center of gravity points in the voxel grid. And (4) processing all voxel grids to obtain point clouds, namely diluted point clouds. The method has the advantages that the number of the point clouds is reduced, and the shape characteristics of the point clouds are saved.
The step S113 includes:
s1131: sequencing the diluted two-dimensional forest fire area point clouds from small to large according to the coordinate value X, and obtaining a vertex sequence p 1 ,p 2 ,...,p n ，
S1133: p is to be 1 And p 2 Put into a point cloud convex hull of a two-dimensional forest fire area from p 3 Starting, when the current point is in the anticlockwise direction of the two-dimensional forest fire area point cloud convex hull, continuing to put the current point into the two-dimensional forest fire area point cloud convex hull, otherwise, sequentially deleting the points which are recently added into the two-dimensional forest fire area point cloud convex hull until a new point is in the anticlockwise direction, repeating the process until the rightmost p is touched n Calculating a lower convex hull of the point cloud convex hull of the two-dimensional forest fire area;
the specific method comprises the following steps: p is a radical of formula i-1 ,p i Is the last two vertexes of the point cloud convex hull of the current two-dimensional forest fire area, q is the vertex of the point cloud convex hull of the current two-dimensional forest fire area to be judged,
is p i-1 To p i Is greater than or equal to>
Is p i-1 The vector to q is judged by a vector product calculation formula>
S1134: p is to be n And p n-1 Put into convex hulls, from p n-2 Starting, when the current point is in the anticlockwise direction of the two-dimensional forest fire area point cloud convex hull, continuously placing the current point into the two-dimensional forest fire area point cloud convex hull, and if not, sequentially deleting the points which are recently added into the two-dimensional forest fire area point cloud convex hull until the new point is in the anticlockwise direction, and solving the upper convex hull of the two-dimensional forest fire area point cloud convex hull;
the specific method comprises the following steps: p is a radical of i-1 ,p i The final two vertexes of the point cloud convex hull of the current two-dimensional forest fire area are shown as q, the vertexes of the point cloud convex hull of the current two-dimensional forest fire area to be judged are shown as q,
is p i-1 To p i Is greater than or equal to>
Is p i-1 The vector to q is judged by a vector product calculation formula>
S1135: and sequentially judging whether points on the two-dimensional forest fire area point cloud convex hull are all on the convex hull, and if not, deleting the points.
The specific method comprises the following steps: using cross product determination of vectors, a = (x) 1 ,y 1 ),b＝(x 2 ,y 2 ),c＝(x 3 ,y 3 ) A, b and c are respectively a current calculation point, a first convex hull point in a current convex hull vertex stack and a second convex hull point in the current convex hull vertex stack,
specifically, software calculates the convex hull of the point cloud data of the two-dimensional mountain fire area through an Andre algorithm based on the horizontal sequence in the convex hull algorithm.
The specific calculation steps are as follows: (1) Sorting x from small to large (if x is the same, sorting y from small to large), and obtaining a sequence p 1 ,p 2 ,...,p n . (2) P is to 1 And p 2 Put into convex hulls, from p 3 Starting, the current point continues in the counterclockwise direction of the "forward" direction of the convex hull, otherwise, deleting the points which are recently added into the convex hull in sequence until the new point is in the counterclockwise direction. This process is repeated until the rightmost p is encountered n The "downward convex hull" is found, and (3) the inverse is found from p n And starting to do the above steps again to obtain the upper convex hull, and combining the upper convex hull and the upper convex hull to form the complete convex hull.
Specifically, whether the point is on the convex hull or not is judged by using the cross product of the vectors.
a＝(x 1 ,y 1 ),b＝(x 2 ,y 2 ),c＝(x 3 ,y 3 ) And a, b and c are respectively a current calculation point, a first convex package point in a current stack and a second convex package point in the current stack.
As shown in fig. 3, the step S12 includes:
s121: calculating the gravity center of the point cloud convex hull of the two-dimensional forest fire area according to the two-dimensional point cloud on the boundary of the point cloud convex hull of the two-dimensional forest fire area; the method comprises the following specific steps:
(1) Setting the average value of all vertexes in the two-dimensional forest fire area point cloud convex hull as a predicted gravity center point G (X, y), and dividing the two-dimensional forest fire area point cloud convex hull into n triangles X through the predicted gravity center point 1 ,X 2 ,...X n The coordinates of three vertexes of the triangle are respectively A (x) 1 ,y 1 ),B(x 2 ,y 2 ),C(x 3 ,y 3 ) Calculating the center of gravity G of each triangle s (x s ,y s ) The coordinates are
Triangle area coordinate of->
(2) Calculating the gravity center of the point cloud convex hull of the two-dimensional forest fire area as G (x, y), -or>
G ix Denotes the center of gravity, S, of the ith triangle i The area of the ith triangle is shown.
S122: and calculating the two-dimensional air route of the unmanned aerial vehicle by an algorithm of scaling up irregular polygons in equal proportion according to the coordinates of each vertex of the two-dimensional forest fire area point cloud convex hull, the gravity center of the two-dimensional forest fire area point cloud convex hull and the preset safe flying distance. The forest fire area in the forest fire area is shown in fig. 4, the software calculates a route path according to the convex hull and the gravity center of the convex hull, and plans the route by an algorithm of enlarging irregular polygons in equal proportion.
The specific calculation steps include: (1) The distance that needs to be expanded outward is L, that is, a preset safe flight distance (L is how far the unmanned aerial vehicle is set to safely fly in a forest fire area according to environmental factors and the like), (2) the vertex coordinates of a single peripheral convex hull are calculated, and as shown in fig. 4, the coordinates are calculated
A is a vertex of a point cloud convex hull of a two-dimensional forest fire area, A' is a corresponding vertex of a two-dimensional air route of the unmanned aerial vehicle, v 1 ,v 2 Respectively calculating the coordinates of A ' by the calculation steps of the vertex A ', B ', C ', D ', E ' and F ', and calculating all point coordinates of the peripheral convex polygon.
As shown in fig. 5, the step S13 is:
s131: the method comprises the steps that original geographical information point clouds corresponding to forest fire area convex hulls one by one are used for obtaining original altitude data, and preset altitude data are added to be used as a course altitude;
s132: judging whether the distance between the vertexes of the two-dimensional route of the unmanned aerial vehicle is larger than a preset distance, if so, judging the actual altitude of the point at each preset distance, calculating whether the height difference between the route altitude of the unmanned aerial vehicle and the actual altitude is larger than a preset altitude difference value, and if not, resetting the route altitude to be the actual altitude plus preset altitude data;
s133: and adding the altitude of the air route to the two-dimensional air route of the unmanned aerial vehicle to obtain the three-dimensional air route of the unmanned aerial vehicle.
Specifically, the software converts the flight path data of the two-dimensional interface into three-dimensional data. The method comprises the following specific steps: the point cloud data of the mountain fire convex hull corresponds to the original point cloud data one by one, and a certain altitude is increased according to the actual situation on the basis of the original altitude. If the distance between the vertexes of the convex hull air route is too large, the altitude of a mountain body and the like of the point is judged on the air route at intervals of preset distance of 50m, the air route height is dynamically set according to the flight height of the unmanned aerial vehicle and the altitude difference of the mountain body, and the risk of explosion of the unmanned aerial vehicle is reduced.
The step S14 includes:
s141: photographing forest fires at a preset monitoring point on a three-dimensional air route of the unmanned aerial vehicle to obtain a first image, keeping current camera parameters unchanged, moving a preset distance from the monitoring point to the gravity center direction of a point cloud convex hull of a two-dimensional forest fire area, and photographing to obtain a second image;
s142: processing the first image and the second image through an opencv image processing library to screen out a forest fire area; the specific method comprises the following steps; (1) Judging corresponding pixel areas of forest fires by RGB, HIS, a set red component threshold value and a set saturation component threshold value of the first image and the second image, and realizing binarization of the images; (2) carrying out noise reduction processing on the binarized image; (3) Expanding the binarized image after the noise reduction treatment to obtain a preprocessed image;
the concrete steps are that 1)And judging the corresponding pixel area of the forest fire by RGB (R is a red component, G is a green component, and B is a blue component), HIS (H is chroma, S is saturation, and I is brightness) and a set threshold value for the picture, thereby realizing binarization of the original picture. S is calculated in a mode that S = (1-3.0 minValue/(R + G + B)), R, G and B are red, green and blue components of a current pixel point respectively, and minValue is the minimum value of the three components of RGB; in forest fire judgment, a preset red component threshold value Rt and a saturation threshold value St are used. The forest fire pixel points meet the following conditions:
and if the current forest fire pixel point meets the condition, judging that the pixel point is fire, displaying the pixel point as white, and otherwise, displaying the pixel point as black.
2) And carrying out noise reduction processing on the binarized image. The median filtering is used, and is a nonlinear signal processing technology which can effectively inhibit noise based on a sequencing statistical theory, so that isolated noise points are eliminated. The two-dimensional median filter output is g (x, y) = med { f (x-k, y-l), (k, l ∈ W) }, where f (x, y), g (x, y) are the original image and the processed image, respectively. W is a two-dimensional template, typically a 3 x 3,5 x 5 region.
3) And (3) expanding the binary image subjected to noise point screening, wherein the expansion is used for communicating boundaries (boundaries of forest fire parts) and can be used for connecting objects which are not connected together.
S143: calculating pixels occupied by the heights of the forest fire areas in the first image and the second image, and calculating the distance between the unmanned aerial vehicle in the forest fire area and the boundary of the current forest fire area through a monocular vision distance measurement algorithm;
the method comprises the following specific steps: 1) Preprocessing image pixels into [ cols, rows ], dividing forest fire regions in a pixel value segmentation mode on the preprocessing image, and setting a central region into behaviors of the image [0.3 × cols and 0.75 × cols ]; 2) Carrying out contour detection FindContours on the preprocessed image, and respectively calculating a bounding rectangle of the minimum positive rectangle of the contour on the obtained contour data; 3) Performing centering judgment on a smallest regular rectangle surrounding a forest fire, searching a centered forest fire frame, judging a rectangular frame, and calculating pixels on the height of the rectangle;
s144: calculating longitude and latitude coordinates of a forest fire area through longitude and latitude coordinates of unmanned aerial vehicle photographing and the head orientation and pitch angle of the unmanned aerial vehicle photographing acquired from an unmanned aerial vehicle built-in system; forest fire area
The method comprises the following specific steps: (1) Calculating the distance L of the forest fire by a distance measurement algorithm of monocular vision dis ，
N 1 The number of pixel points of the measured object image height before the unmanned aerial vehicle moves; n is a radical of 2 The number of the pixel points of the height of the measured object image after the unmanned aerial vehicle moves is X, and the X is the moving distance of the object image observed by the unmanned aerial vehicle;
(2) Calculating longitude and latitude information of a forest fire area according to longitude and latitude coordinates of photographing by the unmanned aerial vehicle before moving, head orientation beta of photographing by the unmanned aerial vehicle acquired from an unmanned aerial vehicle built-in system and pitch angle alpha information; the method comprises the following specific steps:
converting into two-dimensional unit vector through unmanned aerial vehicle aircraft nose direction
Based on the formula of the vector product>
Get->
Since square roots have no negative number, [ lambda ] therefore +>
Wherein y is f Is the Y-axis vector component of the machine head projection direction, because the machine head direction is different, the distance between the unmanned aerial vehicle of the horizontal two-dimensional space and the forest fire is L xy ，L xy ＝L dis * cos (alpha), the longitude and latitude coordinates before the unmanned aerial vehicle moves are mapped into point cloud coordinates (x) through UTM projection s ，y s ，z s ) Setting the coordinate of the forest fire position as->
And obtaining the area coordinates of the forest fire.
S145: and judging whether the distance from the longitude and latitude coordinates of the forest fire area to the three-dimensional route is greater than a preset safety distance, if so, adding the longitude and latitude coordinates of the forest fire area into the coordinates of the forest fire area without action, and if not, adding the longitude and latitude coordinates of the forest fire area into the coordinates of the forest fire area to regenerate the three-dimensional route of the unmanned aerial vehicle. The method comprises the following specific steps:
(1) Judging the distance from the existing route to the forest fire, if L is more than 1.1L xy Not updated, if L < 1.1X L xy Updating the current route;
and if the route is to be updated, adding the current forest fire point coordinate into the forest fire area coordinate, repeating the steps S11, S12 and S13, setting the current unmanned aerial vehicle position as a starting point and updating the three-dimensional route.
As shown in fig. 6, an embodiment of the present invention further provides an automatic forest fire photographing tracking apparatus based on an unmanned aerial vehicle, including:
the forest fire convex hull generating module 21 is used for receiving the position coordinates of the forest fire area and generating a forest fire area convex hull according to the original geographic information point cloud;
the two-dimensional route generation module 22 is used for generating the two-dimensional route of the unmanned aerial vehicle according to the convex hull of the forest fire area;
the three-dimensional route generation module 23 is used for generating a three-dimensional route of the unmanned aerial vehicle according to the original geographic information point cloud and the two-dimensional route of the unmanned aerial vehicle;
and the forest fire dynamic monitoring module 24 is used for dynamically monitoring whether the three-dimensional air route of the unmanned aerial vehicle threatens forest fire, and if so, updating the position coordinates of the forest fire area to regenerate the three-dimensional air route of the unmanned aerial vehicle.
It should be noted that the forest fire convex hull generating module 21 includes:
the two-dimensional forest fire point cloud generating unit is used for receiving the position coordinates of the forest fire area and generating a two-dimensional forest fire area point cloud according to the original geographic information point cloud;
the two-dimensional forest fire point cloud diluting unit is used for diluting the two-dimensional forest fire area point cloud to obtain a diluted two-dimensional forest fire area point cloud;
and the two-dimensional forest fire convex hull calculating unit is used for calculating the convex hull of the diluted two-dimensional forest fire area point cloud through an Andre algorithm based on a horizontal sequence in the convex hull algorithm to obtain the two-dimensional forest fire area point cloud convex hull.
It should be noted that the two-dimensional route generation module 22 includes:
the forest fire convex hull gravity center calculating unit is used for calculating the gravity center of the two-dimensional forest fire area point cloud convex hull according to the two-dimensional point cloud on the boundary of the two-dimensional forest fire area point cloud convex hull;
and the unmanned aerial vehicle two-dimensional route calculation unit is used for calculating the two-dimensional route of the unmanned aerial vehicle through an algorithm for amplifying irregular polygons in equal proportion according to the coordinates of each vertex of the two-dimensional forest fire area point cloud convex hull, the gravity center of the two-dimensional forest fire area point cloud convex hull and the preset safe flying distance.
It should be noted that the three-dimensional route generation module 23 includes:
the system comprises a route altitude acquisition unit, a route searching unit and a route searching unit, wherein the route altitude acquisition unit is used for acquiring original altitude data by mapping the forest fire area convex hulls to original geographic information point clouds one by one, and adding preset altitude data as a route altitude;
the actual altitude calculation unit is used for judging whether the distance between vertexes of the two-dimensional air route of the unmanned aerial vehicle is larger than a preset distance or not, if so, judging the actual altitude of the point at each preset distance, calculating whether the altitude difference between the air route altitude of the unmanned aerial vehicle and the actual altitude is larger than a preset altitude difference or not, and if not, resetting the air route altitude to be the actual altitude plus preset altitude data;
and the unmanned aerial vehicle three-dimensional route generation unit is used for adding the route altitude to the unmanned aerial vehicle two-dimensional route to obtain the unmanned aerial vehicle three-dimensional route.
It should be noted that the forest fire dynamic monitoring module 24 includes:
the system comprises a monitoring image acquisition unit, a data acquisition unit and a data processing unit, wherein the monitoring image acquisition unit is used for photographing forest fires at a preset monitoring point on a three-dimensional route of the unmanned aerial vehicle to obtain a first image, keeping current camera parameters unchanged, moving a preset distance from the monitoring point to the gravity center direction of a point cloud convex hull of a two-dimensional forest fire area, and then photographing to obtain a second image;
the forest fire area screening unit is used for processing the first image and the second image through the opencv image processing library and screening out a forest fire area;
the forest fire distance calculating unit is used for calculating pixels occupied by heights of the forest fire areas in the first image and the second image, and calculating the distance between the unmanned aerial vehicle in the forest fire areas and the boundary of the current forest fire areas through a monocular vision distance measuring algorithm;
the forest fire coordinate calculating unit is used for calculating the longitude and latitude coordinates of a forest fire area through the longitude and latitude coordinates photographed by the unmanned aerial vehicle and the head orientation and the pitch angle of the unmanned aerial vehicle photographed, which are acquired from an unmanned aerial vehicle built-in system;
and the forest fire safety judging unit is used for judging whether the distance from the longitude and latitude coordinates of the forest fire area to the three-dimensional air route is greater than a preset safety distance, if so, adding the longitude and latitude coordinates of the forest fire area into the coordinates of the forest fire area without action, and if not, adding the longitude and latitude coordinates of the forest fire area into the coordinates of the forest fire area to regenerate the three-dimensional air route of the unmanned aerial vehicle.
The embodiment of the invention also provides an automatic forest fire photographing and tracking system based on the unmanned aerial vehicle, which comprises the following components: a memory for storing a computer program; and the processor is used for executing a computer program to realize the steps of the automatic photographing and tracking method for the forest fire based on the unmanned aerial vehicle.
The embodiment of the invention also provides a readable storage medium, wherein the readable storage medium stores a computer program, and the computer program is executed by a processor to realize the steps of the automatic forest fire photographing and tracking method based on the unmanned aerial vehicle.
For the description of the features in the embodiment corresponding to fig. 6, reference may be made to the related description of the embodiments corresponding to fig. 1 to fig. 5, which is not repeated here.
The method, the device and the system for automatically photographing and tracking the forest fire based on the unmanned aerial vehicle are described in detail above. The embodiments are described in a progressive mode in the specification, the emphasis of each embodiment is on the difference from the other embodiments, and the same and similar parts among the embodiments can be referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description. It should be noted that, for those skilled in the art, without departing from the principle of the present invention, it is possible to make various improvements and modifications to the present invention, and those improvements and modifications also fall within the scope of the claims of the present invention.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
Claims (5)
1. An automatic photographing and tracking method for forest fires based on an unmanned aerial vehicle is characterized by comprising the following steps:
receiving the position coordinates of the forest fire area, respectively setting the limited ranges of an X axis and a Y axis in the direct filtering according to the position coordinates of the forest fire area, and cutting the original geographic information point cloud to obtain the forest fire area point cloud;
projecting the forest fire area point cloud to a two-dimensional plane to obtain a two-dimensional forest fire area point cloud;
according to parameter information of the two-dimensional forest fire area point cloud, a three-dimensional voxel grid is created through a Voxelgrid filter;
representing all points in the three-dimensional voxel grid through a gravity center point in the three-dimensional voxel grid to obtain a diluted two-dimensional forest fire area point cloud;
sequencing the diluted two-dimensional forest fire area point clouds from small to large according to the coordinate value X, and obtaining a vertex sequence p 1 ，p 2 ，...，p n ；
P is to be 1 And p 2 Putting the point cloud into a convex hull of a two-dimensional forest fire area point cloud from p 3 Starting, when the current point is in the anticlockwise direction of the two-dimensional forest fire area point cloud convex hull, continuing to put the current point into the two-dimensional forest fire area point cloud convex hull, otherwise, sequentially deleting the points which are recently added into the two-dimensional forest fire area point cloud convex hull until a new point is in the anticlockwise direction, repeating the process until the rightmost p is touched n Calculating a lower convex hull of the point cloud convex hull of the two-dimensional forest fire area;
p is to be n And p n-1 Putting the point cloud into a convex hull of a two-dimensional forest fire area point cloud from p n-2 Starting, when the current point is in the anticlockwise direction of the two-dimensional forest fire area point cloud convex hull, continuing to put the current point into the two-dimensional forest fire area point cloud convex hull, otherwise, sequentially deleting the points which are recently added into the two-dimensional forest fire area point cloud convex hull until a new point is in the anticlockwise direction, repeating the process until the leftmost p is touched 1 Solving an upper convex hull of the point cloud convex hull of the two-dimensional forest fire area;
sequentially judging whether points on a two-dimensional forest fire area point cloud convex hull are all on the convex hull, and if not, deleting the points;
calculating the gravity center of the point cloud convex hull of the two-dimensional forest fire area according to the two-dimensional point cloud on the boundary of the point cloud convex hull of the two-dimensional forest fire area;
calculating a two-dimensional air route of the unmanned aerial vehicle by an algorithm of scaling up irregular polygons in equal proportion according to coordinates of each vertex of the two-dimensional forest fire area point cloud convex hull, the gravity center of the two-dimensional forest fire area point cloud convex hull and a preset safe flying distance;
the method comprises the steps that original geographical information point clouds corresponding to forest fire area convex hulls one by one are used for obtaining original altitude data, and preset altitude data are added to be used as a course altitude;
judging whether the distance between the vertexes of the two-dimensional route of the unmanned aerial vehicle is larger than a preset distance, if so, judging the actual altitude of the point at each preset distance, calculating whether the height difference between the route altitude of the unmanned aerial vehicle and the actual altitude is larger than a preset altitude difference value, and if not, resetting the route altitude to be the actual altitude plus preset altitude data;
adding the air route altitude to the two-dimensional air route of the unmanned aerial vehicle to obtain a three-dimensional air route of the unmanned aerial vehicle;
taking a picture of forest fire at a preset monitoring point on a three-dimensional route of the unmanned aerial vehicle to obtain a first image, keeping current camera parameters unchanged, moving a preset distance from the monitoring point to the gravity center direction of a point cloud convex hull of a two-dimensional forest fire area, and taking a picture to obtain a second image;
processing the first image and the second image through an opencv image processing library to screen out forest fire areas;
calculating pixels occupied by the heights of the forest fire areas in the first image and the second image, and calculating the distance between the unmanned aerial vehicle in the forest fire area and the boundary of the current forest fire area through a monocular vision distance measurement algorithm;
calculating longitude and latitude coordinates of a forest fire area through longitude and latitude coordinates of unmanned aerial vehicle photographing and the head orientation and pitch angle of the unmanned aerial vehicle photographing acquired from an unmanned aerial vehicle built-in system;
and judging whether the distance from the longitude and latitude coordinates of the forest fire area to the three-dimensional route is greater than a preset safety distance, if so, adding the longitude and latitude coordinates of the forest fire area into the coordinates of the forest fire area without action, and if not, adding the longitude and latitude coordinates of the forest fire area into the coordinates of the forest fire area to regenerate the three-dimensional route of the unmanned aerial vehicle.
2. The utility model provides an automatic tracking means that shoots of forest fire based on unmanned aerial vehicle which characterized in that includes:
the forest fire convex hull generating module is used for receiving the position coordinates of the forest fire area, respectively setting the limiting ranges of an X axis and a Y axis in the direct filtering according to the position coordinates of the forest fire area, and cutting the original geographic information point cloud to obtain the forest fire area point cloud;
projecting the forest fire area point cloud to a two-dimensional plane to obtain a two-dimensional forest fire area point cloud;
according to the parameter information of the point cloud of the two-dimensional forest fire area, a three-dimensional voxel grid is created through a VoxeIGrid filter; representing all points in the three-dimensional voxel grid through a gravity center point in the three-dimensional voxel grid to obtain a diluted two-dimensional forest fire area point cloud; sequencing the diluted two-dimensional forest fire area point clouds from small to large according to the coordinate value X, and obtaining a vertex sequence p 1 ，p 2 ，...，p n (ii) a P is to be 1 And p 2 Put into a point cloud convex hull of a two-dimensional forest fire area from p 3 Starting, when the current point is in the anticlockwise direction of the two-dimensional forest fire area point cloud convex hull, continuing to put the current point into the two-dimensional forest fire area point cloud convex hull, otherwise, sequentially deleting the points which are recently added into the two-dimensional forest fire area point cloud convex hull until a new point is in the anticlockwise direction, repeating the process until the rightmost p is touched n Calculating a lower convex hull of the point cloud convex hull of the two-dimensional forest fire area; p is to be n And p n-1 Put into a point cloud convex hull of a two-dimensional forest fire area from p n-2 Starting, when the current point is in the anticlockwise direction of the two-dimensional forest fire area point cloud convex hull, continuing to put the current point into the two-dimensional forest fire area point cloud convex hull, otherwise, sequentially deleting the points which are recently added into the two-dimensional forest fire area point cloud convex hull until a new point is in the anticlockwise direction, repeating the process until the leftmost p is touched 1 Solving an upper convex hull of the point cloud convex hull of the two-dimensional forest fire area;
the two-dimensional route generation module is used for sequentially judging whether points on the two-dimensional forest fire area point cloud convex hull are all on the convex hull or not, and if not, deleting the points; calculating the gravity center of the point cloud convex hull of the two-dimensional forest fire area according to the two-dimensional point cloud on the boundary of the point cloud convex hull of the two-dimensional forest fire area; calculating a two-dimensional air route of the unmanned aerial vehicle by an algorithm of scaling up irregular polygons in equal proportion according to coordinates of each vertex of the two-dimensional forest fire area point cloud convex hull, the gravity center of the two-dimensional forest fire area point cloud convex hull and a preset safe flying distance;
the three-dimensional route generation module is used for corresponding the convex hulls of the forest fire area to the original geographic information point clouds one by one to obtain original elevation data, and the original elevation data and the preset elevation data are used as the route elevation; judging whether the distance between the vertexes of the two-dimensional route of the unmanned aerial vehicle is larger than a preset distance, if so, judging the actual altitude of the point at each preset distance, calculating whether the height difference between the route altitude of the unmanned aerial vehicle and the actual altitude is larger than a preset altitude difference value, and if not, resetting the route altitude to be the actual altitude plus preset altitude data; adding the air route altitude to the two-dimensional air route of the unmanned aerial vehicle to obtain a three-dimensional air route of the unmanned aerial vehicle;
the system comprises a forest fire dynamic monitoring module, a first image acquisition module, a second image acquisition module and a third image acquisition module, wherein the forest fire dynamic monitoring module is used for photographing forest fires at a preset monitoring point on a three-dimensional air route of the unmanned aerial vehicle to acquire a first image, keeping current camera parameters unchanged, and moving a preset distance from the monitoring point to the gravity center direction of a point cloud convex hull of a two-dimensional forest fire area to photograph to acquire a second image; processing the first image and the second image through an opencv image processing library to screen out forest fire areas; calculating pixels occupied by the heights of the forest fire areas in the first image and the second image, and calculating the distance between the unmanned aerial vehicle in the forest fire area and the boundary of the current forest fire area through a monocular vision distance measurement algorithm; calculating longitude and latitude coordinates of a forest fire area through longitude and latitude coordinates of unmanned aerial vehicle photographing and the head orientation and pitch angle of the unmanned aerial vehicle photographing acquired from an unmanned aerial vehicle built-in system; and judging whether the distance from the longitude and latitude coordinates of the forest fire area to the three-dimensional route is greater than a preset safety distance, if so, adding the longitude and latitude coordinates of the forest fire area into the coordinates of the forest fire area without action, and if not, adding the longitude and latitude coordinates of the forest fire area into the coordinates of the forest fire area to regenerate the three-dimensional route of the unmanned aerial vehicle.
3. The automatic forest fire photographing and tracking device based on the unmanned aerial vehicle as claimed in claim 2, wherein the forest fire convex hull generating module comprises:
the two-dimensional forest fire point cloud generating unit is used for receiving the position coordinates of the forest fire area, respectively setting the limiting ranges of an X axis and a Y axis in the direct filtering according to the position coordinates of the forest fire area, and cutting the original geographic information point cloud to obtain the forest fire area point cloud; projecting the forest fire area point cloud to a two-dimensional plane to obtain a two-dimensional forest fire area point cloud;
the two-dimensional forest fire point cloud diluting unit is used for creating a three-dimensional voxel grid through a VoxeIGrid filter according to the parameter information of the two-dimensional forest fire area point cloud; representing all points in the three-dimensional voxel grid through a gravity center point in the three-dimensional voxel grid to obtain a diluted two-dimensional forest fire area point cloud;
the two-dimensional forest fire convex hull calculating unit is used for calculating the convex hull of the diluted two-dimensional forest fire area point cloud through an Andre algorithm based on a horizontal sequence in the convex hull algorithm, sequencing the diluted two-dimensional forest fire area point cloud from small to large according to the size of a coordinate value X, and obtaining a vertex sequence p 1 ，p 2 ，...，p n (ii) a P is to be 1 And p 2 Put into a point cloud convex hull of a two-dimensional forest fire area from p 3 Starting, when the current point is in the anticlockwise direction of the two-dimensional forest fire area point cloud convex hull, continuing to put the point cloud convex hull in the two-dimensional forest fire area point cloud, otherwise, sequentially deleting the points which are recently added into the point cloud convex hull in the two-dimensional forest fire area point cloud until the new point is in the anticlockwise direction, repeating the process until the rightmost p is touched n Calculating a lower convex hull of the point cloud convex hull of the two-dimensional forest fire area; p is to be n And p n-1 Put into a point cloud convex hull of a two-dimensional forest fire area from p n-2 Starting, when the current point is in the anticlockwise direction of the two-dimensional forest fire area point cloud convex hull, continuously placing the current point into the two-dimensional forest fire area point cloud convex hull, otherwise, sequentially deleting the points which are recently added into the two-dimensional forest fire area point cloud convex hull until a new point is in the anticlockwise direction, repeating the process until the point touches the leftmost p1, and solving the upper convex hull of the two-dimensional forest fire area point cloud convex hull; and sequentially judging whether points on the two-dimensional forest fire area point cloud convex hull are all on the convex hull, and if not, deleting the points.
4. The utility model provides an automatic tracker that shoots of forest fire based on unmanned aerial vehicle which characterized in that includes:
a memory for storing a computer program;
a processor for executing the computer program to implement the steps of the unmanned aerial vehicle-based forest fire automatic photographing tracking method according to claim 1.
5. A readable storage medium, characterized in that the readable storage medium stores a computer program, which when executed by a processor implements the steps of the unmanned aerial vehicle-based forest fire automatic photo tracking method according to claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110484192.8A CN113190031B (en) | 2021-04-30 | 2021-04-30 | Forest fire automatic photographing and tracking method, device and system based on unmanned aerial vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110484192.8A CN113190031B (en) | 2021-04-30 | 2021-04-30 | Forest fire automatic photographing and tracking method, device and system based on unmanned aerial vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113190031A CN113190031A (en) | 2021-07-30 |
| CN113190031B true CN113190031B (en) | 2023-03-24 |
Family
ID=76983676
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110484192.8A Active CN113190031B (en) | 2021-04-30 | 2021-04-30 | Forest fire automatic photographing and tracking method, device and system based on unmanned aerial vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113190031B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114758465B (en) * | 2022-03-30 | 2024-03-15 | 南京林业大学 | Forest protection method based on unmanned cluster cooperative intelligent technology |
| CN115793716B (en) * | 2023-02-13 | 2023-05-09 | 成都翼比特自动化设备有限公司 | Automatic optimization method and system for unmanned aerial vehicle route |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104596516A (en) * | 2014-11-24 | 2015-05-06 | 中国海洋大学 | Unmanned aerial vehicle coverage flight path planning based on dynamic newly-added adjacent area |
| CN110047241A (en) * | 2019-04-27 | 2019-07-23 | 刘秀萍 | A kind of forest fire unmanned plane cruise monitoring system |
Family Cites Families (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105550692B (en) * | 2015-12-30 | 2018-08-31 | 南京邮电大学 | The homing vector landing concept of unmanned plane based on marker color and contour detecting |
| CN107315410B (en) * | 2017-06-16 | 2020-05-29 | 江苏科技大学 | Automatic obstacle removing method for robot |
| CN107478231A (en) * | 2017-08-10 | 2017-12-15 | 千寻位置网络有限公司 | Unmanned plane Route Planning Algorithm based on polygon obstacle detection |
| CN108897312B (en) * | 2018-05-14 | 2021-06-04 | 南开大学 | Method for planning continuous monitoring path of multiple unmanned aerial vehicles to large-scale environment |
| CN109191761A (en) * | 2018-09-06 | 2019-01-11 | 中国石油大学(华东) | A kind of method for recognizing fire disaster based on flame multiple features fusion |
| US11106223B2 (en) * | 2019-05-09 | 2021-08-31 | GEOSAT Aerospace & Technology | Apparatus and methods for landing unmanned aerial vehicle |
| CN110210428B (en) * | 2019-06-06 | 2021-02-05 | 北京林业大学 | MSER-based smoke root node detection method in remote complex environment |
| CN110276284A (en) * | 2019-06-11 | 2019-09-24 | 暨南大学 | Flame identification method, device, equipment and storage medium based on video quality assessment |
| US11823460B2 (en) * | 2019-06-14 | 2023-11-21 | Tusimple, Inc. | Image fusion for autonomous vehicle operation |
| CN110457736B (en) * | 2019-06-19 | 2022-10-11 | 南京邮电大学 | Markov chain based fire prediction in RCRSS |
| CN110160533B (en) * | 2019-07-03 | 2022-02-25 | 安徽工程大学 | Path planning method for obstacle avoidance of mobile robot under multi-convex hull obstacle model |
| CN209963643U (en) * | 2019-07-31 | 2020-01-17 | 成都翼比特自动化设备有限公司 | Transmission line foreign matter removing equipment based on unmanned aerial vehicle |
| CN110544298B (en) * | 2019-08-29 | 2023-06-30 | 中国南方电网有限责任公司 | Substation modeling method, device, computer equipment and storage medium |
| CN111898440B (en) * | 2020-06-30 | 2023-12-01 | 成都思晗科技股份有限公司 | Mountain fire detection method based on three-dimensional convolutional neural network |
| CN112129298A (en) * | 2020-09-28 | 2020-12-25 | 广州极飞科技有限公司 | Method, device and equipment for determining unmanned aerial vehicle air route and storage medium |
| CN112351438B (en) * | 2020-11-04 | 2022-12-02 | 南京航空航天大学 | Unmanned aerial vehicle base station deployment method based on undirected graph |
-
2021
- 2021-04-30 CN CN202110484192.8A patent/CN113190031B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104596516A (en) * | 2014-11-24 | 2015-05-06 | 中国海洋大学 | Unmanned aerial vehicle coverage flight path planning based on dynamic newly-added adjacent area |
| CN110047241A (en) * | 2019-04-27 | 2019-07-23 | 刘秀萍 | A kind of forest fire unmanned plane cruise monitoring system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113190031A (en) | 2021-07-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113034689B (en) | Laser point cloud-based terrain three-dimensional model, terrain map construction method and system, and storage medium | |
| US8116530B2 (en) | Map change detection device, map change detection method, and program | |
| CN113190031B (en) | Forest fire automatic photographing and tracking method, device and system based on unmanned aerial vehicle | |
| KR101924278B1 (en) | Apparatus and method for extraction of tidal creeks in tidal flat zones using drone | |
| KR20180131932A (en) | River topography information generation method using drone and geospatial information | |
| JP5817422B2 (en) | Building extraction apparatus, method and program | |
| CN112344869B (en) | Iron tower deformation monitoring method and system based on side fitting | |
| CN108195736B (en) | Method for extracting vegetation canopy clearance rate through three-dimensional laser point cloud | |
| CN113187671B (en) | Method for determining yaw angle of wind wheel by using unmanned aerial vehicle | |
| KR101549155B1 (en) | Method of automatic extraction of building boundary from lidar data | |
| CN113345094A (en) | Electric power corridor safety distance analysis method and system based on three-dimensional point cloud | |
| JP6146731B2 (en) | Coordinate correction apparatus, coordinate correction program, and coordinate correction method | |
| CN113378754B (en) | Bare soil monitoring method for construction site | |
| KR101079475B1 (en) | A system for generating 3-dimensional urban spatial information using point cloud filtering | |
| CN114078211A (en) | Method for intelligently detecting tree lodging based on laser radar | |
| CN111895907B (en) | Electricity tower point cloud extraction method, system and equipment | |
| CN116091709B (en) | Three-dimensional reconstruction method and device for building, electronic equipment and storage medium | |
| CN111080536A (en) | Self-adaptive filtering method for airborne laser radar point cloud | |
| CN116052023A (en) | Three-dimensional point cloud-based electric power inspection ground object classification method and storage medium | |
| KR102587445B1 (en) | 3d mapping method with time series information using drone | |
| KR101079531B1 (en) | A system for generating road layer using point cloud data | |
| CN115223090A (en) | Airport clearance barrier period monitoring method based on multi-source remote sensing image | |
| KR101083902B1 (en) | A system for generating 3-dimensional spatial information using an aerial lidar surveying data | |
| KR101079359B1 (en) | A system for generating digital map using an aerial photograph and aerial light detection of ranging data | |
| KR101103491B1 (en) | A system and method for generating road layer using an aerial light detection and ranging data |
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 |