[go: up one dir, main page]

CN118816899B - Unmanned aerial vehicle path planning method, unmanned aerial vehicle path planning device, terminal and storage medium - Google Patents

Unmanned aerial vehicle path planning method, unmanned aerial vehicle path planning device, terminal and storage medium Download PDF

Info

Publication number
CN118816899B
CN118816899B CN202411312008.1A CN202411312008A CN118816899B CN 118816899 B CN118816899 B CN 118816899B CN 202411312008 A CN202411312008 A CN 202411312008A CN 118816899 B CN118816899 B CN 118816899B
Authority
CN
China
Prior art keywords
viewpoint
plane
quality
candidate
sight
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
Application number
CN202411312008.1A
Other languages
Chinese (zh)
Other versions
CN118816899A (en
Inventor
熊卫丹
黄惠
胡梓榆
张洪芊
曾博川
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen University
Original Assignee
Shenzhen University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen University filed Critical Shenzhen University
Priority to CN202411312008.1A priority Critical patent/CN118816899B/en
Publication of CN118816899A publication Critical patent/CN118816899A/en
Application granted granted Critical
Publication of CN118816899B publication Critical patent/CN118816899B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/20—Instruments for performing navigational calculations
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Automation & Control Theory (AREA)
  • Processing Or Creating Images (AREA)

Abstract

The invention discloses an unmanned aerial vehicle path planning method, a device, a terminal and a storage medium, wherein the method determines a candidate view point set according to a two-dimensional base map and a safe flight height; generating an initial viewpoint set according to a candidate viewpoint set based on plane quality and viewpoint plane pair quality, wherein the plane quality is used for measuring texture quality of a single plane, the viewpoint plane pair quality is used for measuring quality of viewpoint plane pairs constructed by the single viewpoint and the plane, optimizing the initial viewpoint set by adopting a multi-objective optimization algorithm to determine an optimized viewpoint set, and determining an unmanned aerial vehicle shooting path according to the candidate viewpoint set and the optimized viewpoint set. According to the invention, the view point set capable of reconstructing high-quality textures is obtained by introducing the plane quality and the view point plane quality, so that the problem that the prior art does not consider how to acquire high-quality image data for texture reconstruction, and the acquired image data cannot achieve an ideal texture effect when used for texture mapping is effectively solved.

Description

Unmanned aerial vehicle path planning method, unmanned aerial vehicle path planning device, terminal and storage medium
Technical Field
The present invention relates to the field of computer graphics, and in particular, to a method, an apparatus, a terminal, and a storage medium for unmanned aerial vehicle path planning.
Background
Construction of large-scale digital twinned cities is typically based on image material acquired by Unmanned aerial vehicles (un-manned AERIAL VEHICLE, UAV) to generate structured models with realistic textures. Current UAV acquisition methods mainly target high quality geometric reconstructions. For example, (1) a volume hierarchical representation is adopted for estimating the cost of each part of a reconstructed scene, two targets of maximizing the information gain of the view points and minimizing the path length are balanced, (2) a scene coverage model is adopted, a sub-module optimization method is formulated for determining the optimal direction of each candidate view point, an integer linear program is used for selecting the optimal path from the candidate view points, the shorter path length is obtained while maximizing the scene coverage, (3) a reconstruction metric prediction reconstruction quality is introduced, a heuristic continuous optimization method is adopted for maximizing the reconstructability of all view points in the scene, 4) a 2.5-dimensional model is estimated for the scene according to the relation between a building and corresponding shadows by adopting an adaptive unmanned aerial vehicle path planning algorithm without field investigation, a minimum view point set is selected by adopting a maximum-minimum optimization method, the reconstruction quality is maximized under the same number of view points, (5) a real-time path planning method for urban scene reconstruction is utilized for generating an initial path by utilizing a top view, the height of the building is estimated by an SLAM (real-time positioning and map construction) frame, and a special photo is shot to reveal the building detail in the two building detail and the minimum path length. These UAV path planning studies work to better and faster reconstruct complete, accurate dense models.
However, these methods do not consider how to acquire high-quality image data for texture reconstruction, so that the acquired image data cannot achieve ideal texture effect when used for texture mapping. When the acquired image is used for texture reconstruction, as the urban building surface has rich straight line characteristics and clear component structures, the problem of imbalance of a cognitive layer is very easy to occur to textures, for example, the perspective relationship of windows of a single building elevation is not uniform, and the like.
Accordingly, there is a need for improvement and development in the art.
Disclosure of Invention
The invention aims to solve the technical problems that aiming at the defects in the prior art, an unmanned aerial vehicle path planning method, an unmanned aerial vehicle path planning device, a unmanned aerial vehicle path planning terminal and a unmanned aerial vehicle storage medium are provided, and aims to solve the problems that how to collect high-quality image data aiming at texture reconstruction is not considered in the prior art, so that the collected image data cannot achieve ideal texture effect when used for texture mapping.
The technical scheme adopted by the invention for solving the problems is as follows:
in a first aspect, an embodiment of the present invention provides a method for planning a path of an unmanned aerial vehicle, where the method includes:
Acquiring a two-dimensional base map and a safe flight height of a target scene, and determining a candidate view point set according to the two-dimensional base map and the safe flight height;
Generating an initial viewpoint set according to the candidate viewpoint set based on plane quality and viewpoint plane pair quality, wherein the plane quality is used for measuring texture quality of a single plane, and the viewpoint plane pair quality is used for measuring quality of a viewpoint plane pair constructed by a single viewpoint and a plane;
Optimizing the initial viewpoint set by adopting a multi-objective optimization algorithm, and determining an optimized viewpoint set;
And determining the unmanned aerial vehicle shooting path according to the candidate viewpoint set and the optimized viewpoint set.
In one implementation method, the generating an initial viewpoint set from the candidate viewpoint set based on the planar quality and the viewpoint planar-to-quality includes:
Constructing a plurality of viewpoint plane pairs based on the candidate viewpoint sets;
Setting an initial line-of-sight direction for a viewpoint in each of the viewpoint plane pairs based on the plane quality;
And calculating the corresponding viewpoint plane pair quality of each viewpoint plane pair, and determining the initial viewpoint set according to each viewpoint plane pair quality.
In one implementation method, the setting an initial line of sight direction for the view in each of the view plane pairs based on the plane quality includes:
sampling in a 180-degree range with the reverse direction of the normal direction of the middle plane of the viewpoint plane as the center, and determining a plurality of candidate sight line directions;
And selecting the corresponding candidate sight line direction when the plane quality is maximum as the initial sight line direction of the viewpoint in the viewpoint plane centering.
In one implementation method, the method for calculating the planar mass includes:
,
Wherein, AndRespectively the perspective quality and the image quality,AndIs the weight;
perspective quality The definition is as follows:
,
Wherein, AndAs the weight of the material to be weighed,Is a set of viewpointsThe number of medium-view points,Measuring unit vectorAndThe distance between the two plates is set to be equal,Representation ofMiddle view pointIs provided with a plurality of lines of sight,Representation ofThe average line of sight direction of the middle view point,Representing a planeNormal vector of (2);
Image quality The definition is as follows:
,
Wherein, AndAs the weight of the material to be weighed,Representing the distance of the line of sightThe value after the normalization is carried out,Representation ofIs provided with a distance between the lines of sight,Representation ofThe average value of the line-of-sight distances of the middle view point,,Representative ofMiddle view point coverage planeIs defined by the width of the region of (a),Representative ofIs a width of (c).
In one implementation method, the method for calculating the quality of the viewpoint plane comprises the following steps:
,
Wherein, AndRespectively the perspective quality and the image quality,AndIs the weight;
perspective quality The definition is as follows:
,
And As the weight of the material to be weighed,Measuring unit vectorAndThe distance between the two plates is set to be equal,Representing a viewpointIs provided with a plurality of lines of sight,Representing a set of viewpointsThe average line of sight direction of the middle view point,Representing a planeNormal vector of (2);
Image quality The definition is as follows:
,
And As the weight of the material to be weighed,Representing the distance of the line of sightThe value after the normalization is carried out,Representing a viewpointIs provided with a distance between the lines of sight,,Representative ofMiddle view point coverage planeIs defined by the width of the region of (a),Representative planeIs defined by the width of the (c) a,Representative planeIs only viewed fromThe observed area duty cycle.
In one implementation, the optimizing the initial viewpoint set using a multi-objective optimization algorithm to determine an optimized viewpoint set includes:
sampling the position and the sight direction in the neighborhood range of each view point in the initial view point set to obtain candidate view point pose corresponding to each view point;
Determining target viewpoint positions in the candidate viewpoint positions based on a multi-target optimization algorithm;
And screening the initial viewpoint set according to the target viewpoint pose corresponding to each viewpoint, and determining the optimized viewpoint set.
In one implementation method, the determining the unmanned aerial vehicle shooting path according to the candidate viewpoint set and the optimized viewpoint set includes:
constructing a full connection diagram according to the candidate viewpoint set and the optimized viewpoint set;
And solving a cost minimum path corresponding to the full-connection graph based on the traveling business problem to serve as the unmanned aerial vehicle shooting path.
In a second aspect, an embodiment of the present invention further provides an unmanned aerial vehicle path planning apparatus, where the unmanned aerial vehicle path planning apparatus includes:
The data acquisition module is used for acquiring a two-dimensional base map and a safe flight height of a target scene, and determining a candidate view point set according to the two-dimensional base map and the safe flight height;
The viewpoint generation module is used for generating an initial viewpoint set according to the candidate viewpoint set based on plane quality and viewpoint plane pair quality, wherein the plane quality is used for measuring texture quality of a single plane, and the viewpoint plane pair quality is used for measuring quality of a viewpoint plane pair constructed by the single viewpoint and the plane;
the viewpoint optimizing module is used for optimizing the initial viewpoint set by adopting a multi-objective optimizing algorithm and determining an optimized viewpoint set;
and the path determining module is used for determining the shooting path of the unmanned aerial vehicle according to the candidate viewpoint set and the optimized viewpoint set.
In a third aspect, an embodiment of the present invention further provides a terminal, where the terminal includes a memory and more than one processor, where the memory stores more than one program, where the program includes instructions for executing the unmanned aerial vehicle path planning method according to any one of the above, and where the processor is configured to execute the program.
In a fourth aspect, an embodiment of the present invention further provides a computer readable storage medium having a plurality of instructions stored thereon, where the instructions are adapted to be loaded and executed by a processor to implement any of the above-mentioned unmanned aerial vehicle path planning methods.
The method and the device have the advantages that the two-dimensional base map and the safe flying height of the target scene are obtained, the candidate viewpoint set is determined according to the two-dimensional base map and the safe flying height, the initial viewpoint set is generated according to the candidate viewpoint set based on plane quality and viewpoint plane pair quality, wherein the plane quality is used for measuring texture quality of a single plane, the viewpoint plane pair quality is used for measuring quality of viewpoint plane pairs constructed by the single viewpoint and the plane, the initial viewpoint set is optimized by adopting a multi-objective optimization algorithm, the optimized viewpoint set is determined, and the unmanned aerial vehicle shooting path is determined according to the candidate viewpoint set and the optimized viewpoint set. According to the invention, the view point set capable of reconstructing high-quality textures is obtained by introducing the plane quality and the view point plane quality, so that the problem that the prior art does not consider how to acquire high-quality image data for texture reconstruction, and the acquired image data cannot achieve an ideal texture effect when used for texture mapping is effectively solved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present invention, and other drawings may be obtained according to the drawings without inventive effort to those skilled in the art.
Fig. 1 is a flow chart of an unmanned aerial vehicle path planning method according to an embodiment of the present invention.
Fig. 2 is a division diagram of a plane lattice generation and a lower probe point provided by an embodiment of the present invention.
Fig. 3 is a schematic plan view of the view point of the present invention.
Fig. 4 is a schematic view of all views of an observable plane provided by an embodiment of the present invention.
Fig. 5 is a schematic diagram of a result of selecting a point of view according to an embodiment of the present invention.
Fig. 6 is a schematic diagram of an initial viewpoint optimization result provided by an embodiment of the present invention.
FIG. 7 is a diagram illustrating texture mapping results according to an embodiment of the present invention.
Fig. 8 is an internal module schematic diagram of an unmanned aerial vehicle path planning device according to an embodiment of the present invention.
Fig. 9 is a schematic block diagram of a terminal according to an embodiment of the present invention.
Detailed Description
The invention discloses a method, a device, a terminal and a storage medium for planning a path of an unmanned aerial vehicle, which are used for making the purposes, the technical scheme and the effects of the invention clearer and more definite, and further detailed description of the invention is provided below by referring to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless expressly stated otherwise, as understood by those skilled in the art. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. The term "and/or" as used herein includes all or any element and all combination of one or more of the associated listed items.
It will be understood by those skilled in the art that all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs unless defined otherwise. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The current UAV acquisition method mainly aims at high-quality geometric reconstruction, and does not consider acquisition of high-quality image data aiming at texture reconstruction, so that ideal texture effect cannot be achieved when the acquired image data is used for texture mapping.
Aiming at the defects in the prior art, the invention provides an unmanned aerial vehicle path planning method, an unmanned aerial vehicle path planning device, a terminal and a storage medium, wherein the method determines a candidate view point set according to a two-dimensional base map and a safe flight height of a target scene by acquiring the two-dimensional base map and the safe flight height; generating an initial viewpoint set according to a candidate viewpoint set based on plane quality and viewpoint plane pair quality, wherein the plane quality is used for measuring texture quality of a single plane, the viewpoint plane pair quality is used for measuring quality of viewpoint plane pairs constructed by the single viewpoint and the plane, optimizing the initial viewpoint set by adopting a multi-objective optimization algorithm to determine an optimized viewpoint set, and determining an unmanned aerial vehicle shooting path according to the candidate viewpoint set and the optimized viewpoint set. According to the invention, the view point set capable of reconstructing high-quality textures is obtained by introducing the plane quality and the view point plane quality, so that the problem that the prior art does not consider how to acquire high-quality image data for texture reconstruction, and the acquired image data cannot achieve an ideal texture effect when used for texture mapping is effectively solved.
Exemplary method
As shown in fig. 1, the method includes:
step S100, acquiring a two-dimensional base map and a safe flight height of a target scene, and determining a candidate view point set according to the two-dimensional base map and the safe flight height;
The two-dimensional bottom map is a two-dimensional overlook bottom map corresponding to the target scene, in the two-dimensional overlook bottom map, each outline polygon represents a building, and the sides of the outline polygons represent building elevation. The safe flight level is the lowest safe flight level of the unmanned aerial vehicle. In this embodiment, a planar lattice that completely covers a target scene is generated based on a two-dimensional base map at a fixed safe flight height H The plane lattice is subjected toAs a candidate view set for subsequent view screening.
As shown in fig. 1, the method specifically further includes:
And step 200, generating an initial viewpoint set according to the candidate viewpoint set based on the plane quality and the viewpoint plane pair quality, wherein the plane quality is used for measuring the texture quality of a single plane, and the viewpoint plane pair quality is used for measuring the quality of a viewpoint plane pair constructed by a single viewpoint and a plane.
Specifically, the plane is a building elevation, and the embodiment defines two quality indexes of plane quality and viewpoint plane quality. The plane quality is based on a group of two-dimensional view points to measure the final texture quality of the plane, and the view point plane pair quality is used for measuring the quality of the two-dimensional view points and the view point plane pair constructed by the plane, and the two qualities are used for guiding the selection of view points. The embodiment generates the initial viewpoint set according to the candidate viewpoint set based on the plane quality and the viewpoint plane quality, so that the initial viewpoint set can maximally cover the building facade in the target scene, and the viewpoints in the initial viewpoint set can be ensured to have high perspective consistency and high image quality.
In one implementation plane quality is used to measure individual planesGiven a set of viewpointsThe method for calculating the plane quality comprises the following steps:
,
Wherein, AndRespectively the perspective quality and the image quality,AndIs the weight;
perspective quality for measuring The sight direction consistency and the sight direction of the middle view point are opposite to each otherTo a degree of (3). Perspective qualityThe definition is as follows:
,
Wherein, AndThe line of sight consistency and the line of sight direction opposite to the weight of the item respectively,Is thatThe number of medium-view points,Measuring unit vectorAndThe distance between the two plates is set to be equal,Representation ofMiddle view pointIs provided with a plurality of lines of sight,Representation ofThe average line of sight direction of the middle view point,Representing a planeNormal vector of (2);
Image quality measures the image quality of planar textures, including the high definition of image material, consistency of image resolution, the integrity of the image overlay plane, and the indispensable degree of the image overlay plane. Given a given MeasuringIs mainly measuredRelative toResolution uniformity and coverage of (a).
Image qualityThe definition is as follows:
,
Wherein, AndThe weights of resolution uniformity and coverage respectively,Is thatThe number of medium-view points,Representing the distance of the line of sightThe value after the normalization is carried out,Representation ofIs provided with a distance between the lines of sight,Representation ofThe average value of the line-of-sight distances of the middle view point,,Representative ofMiddle view point coverage planeIs defined by the width of the region of (a),Representative ofIs a width of (c).
In one implementation, a givenIs a single viewpoint ofMeasuringAnd plane surfaceThe constructed viewpoint plane pairs. The method for calculating the quality of the viewpoint plane comprises the following steps:
,
Wherein, AndRespectively the perspective quality and the image quality,AndIs the weight;
Perspective quality measurement Is the line of sight direction and the average line of sight directionConsistency of (C), andIs opposite toTo a degree of (3). Perspective qualityThe definition is as follows:
,
And As the weight of the material to be weighed,Measuring unit vectorAndThe distance between the two plates is set to be equal,Representing a viewpointIs provided with a plurality of lines of sight,Representing a set of viewpointsThe average line of sight direction of the middle view point,Representing a planeNormal vector of (2);
the image quality mainly considers the high definition, coverage, and indispensable degree of the viewpoint with respect to the plane. Image quality The definition is as follows:
,
And As the weight of the material to be weighed,Representing the distance of the line of sightThe value after the normalization is carried out,Representing a viewpointIs provided with a distance between the lines of sight,,Representative ofMiddle view point coverage planeIs defined by the width of the region of (a),Representative planeIs defined by the width of the (c) a,Representative planeIs only viewed fromThe observed area duty cycle.
In one implementation, the generating an initial viewpoint set from the candidate viewpoint set based on the planar quality and the viewpoint planar-to-quality includes:
step S201, constructing a plurality of viewpoint plane pairs based on the candidate viewpoint sets;
Step S202, setting initial sight line directions for the viewpoints in the viewpoint plane pairs based on the plane quality;
Step S203, calculating the quality of each viewpoint plane pair corresponding to the viewpoint plane pair, and determining the initial viewpoint set according to the quality of each viewpoint plane pair.
Specifically, the step of generating an initial viewpoint set according to the candidate viewpoint set comprises (1) viewpoint plane pair construction, (2) viewpoint direction initialization, and (3) downward-looking viewpoint selection.
(1) Viewpoint plane pair construction. The method for constructing a plurality of viewpoint plane pairs according to the candidate viewpoint sets comprises the following steps ofSetting five unmanned aerial vehicle shooting visual angles including a vertical downward visual angle and four oblique visual angles at each visual angle position, and based on candidate visual point setsThe unmanned plane is designed to vertically descend from the height H to generate a lower detection point for shooting the building elevation at a low height. As shown in fig. 2, according to the minimum distance from the viewpoint to the plane polygon and the threshold value of the safety distance, the methodThe viewpoint in (a) is divided into a downward-searchable viewpoint and a non-downward-searchable viewpoint, and for each downward-searchable viewpoint, a plane that the viewpoint can observe is detected and a pair of viewpoint planes is constructed as shown in fig. 3 and 4. For plane surfacesAll observedIs composed ofIs a set of point of reference. In one implementation, the non-downward-looking point of view may also be employed to form a point-of-view plane pair with the plane.
(2) The viewpoint direction is initialized. Constructing the viewpoint plane pairs later, initializing the sight line directions of the viewpoint plane pairs to the middle viewpoint, and selecting an initial sight line direction for each viewpoint. The step of initializing the view direction includes centering a plane in the view planeUniformly sampling within 180 DEG with the reverse direction of the normal direction as the center, and determining a plurality of candidate sight line directionsSelecting the candidate sight line direction corresponding to the maximum plane quality as the initial sight line direction of the viewpoint in the viewpoint plane centering direction. The viewpoint direction initializing step further includes, before determining the candidate line of sight direction, assigning the same line of sight direction to each viewpoint.
(3) And (5) selecting a point of view. The downviewpoint selects a redundant viewpoint in the viewpoint set for deleting the corresponding plane. The present embodiment adopts a strategy of iterative deletion. In each iteration, first, the respective viewpoint plane pair quality is calculated for each viewpoint plane pair corresponding to each viewpoint plane pairViewpoint(s)Quality based on viewpointWith a corresponding planeThe sum of the masses of the constructed viewpoint plane pairs is calculated to:
,
for each iteration, the view with the lowest quality value is deleted until no redundant view exists, as shown in fig. 5, the iteration is terminated, and the rest views are determined as an initial view point set.
As shown in fig. 1, the method specifically further includes:
and step S300, optimizing the initial viewpoint set by adopting a multi-objective optimization algorithm, and determining an optimized viewpoint set.
And for the viewpoints in the initial viewpoint set, optimizing the positions and directions of the viewpoints by adopting a multi-target optimization algorithm, so that the plane quality is optimized, and the time cost for acquiring images by the unmanned aerial vehicle is reduced. In this embodiment, the optimization target item of the multi-target optimization algorithm includes the number of three-dimensional hover points C required for the entire target scene. In addition, in order to improve the texture quality of the building facade, the optimization targets also comprise view pointsObservable building facadeRespectively corresponding planar mass. The target items of the multi-target optimization are:
,
The method for solving the number of the three-dimensional hovering points is that for a given viewpoint (two-dimensional down-looking point) And plane surfaceIn the followingUniformly sampling the positions of the images from top to bottom longitudinally to generate a series of longitudinal three-dimensional viewpointsWherein, the method comprises the steps of, wherein,Representing the position of the three-dimensional viewpoint,Representing the line of sight direction of the three-dimensional viewpoint.The building elevation is completely covered with a certain overlapping in the height direction. The two-dimensional downward detection points at the same position can have different sight directions for observing different building facades, thusThe corresponding longitudinal three-dimensional view points of the positions of the two-dimensional view points can be longitudinally combined by longitudinally fine-adjusting the positions of the two-dimensional view points. And after longitudinal combination, the number of the three-dimensional hovering points of the whole target scene can be calculated.
In one implementation, the optimizing the initial viewpoint set using the multi-objective optimization algorithm, determining an optimized viewpoint set includes:
step S301, sampling the position and the sight direction in the neighborhood range of each view point in the initial view point set to obtain candidate view point positions corresponding to each view point;
Step S302, determining target viewpoint pose in the candidate viewpoint pose based on a multi-target optimization algorithm;
step S303, screening the initial viewpoint set according to the target viewpoint pose corresponding to each viewpoint, and determining the optimized viewpoint set.
Specifically, the present embodiment adopts the following iterative optimization procedure to achieve the objective item of the minimum multi-objective optimization algorithm. In each iteration, first at the viewpointAnd searching all candidate combinations through a multi-target optimization algorithm to obtain the optimal combination of the viewpoint position and the sight line direction, and taking the optimal combination of the viewpoint position and the sight line direction as an optimized viewpoint pose, namely a target viewpoint pose. And secondly, judging redundancy of other viewpoints again according to the target viewpoint pose and viewpoint plane pair quality, and deleting the redundant viewpoints. When all the undershot points no longer change, then the optimization is determined to converge, and the set of optimized points is determined, as shown in FIG. 6.
As shown in fig. 1, the method specifically further includes:
And step 400, determining an unmanned aerial vehicle shooting path according to the candidate viewpoint set and the optimized viewpoint set.
The embodiment forms a total unmanned aerial vehicle viewpoint set through the candidate viewpoint set and the optimized viewpoint set. And generating a path based on the total unmanned aerial vehicle viewpoint set, and obtaining an unmanned aerial vehicle shooting path.
In one implementation, the determining the unmanned aerial vehicle shooting path according to the candidate viewpoint set and the optimized viewpoint set includes:
Step S401, constructing a full connection diagram according to the candidate viewpoint set and the optimized viewpoint set;
and step S402, solving a cost minimum path corresponding to the full-connection diagram based on the traveling merchant problem to serve as the unmanned aerial vehicle shooting path.
In order to reduce the time cost of image acquisition of the unmanned aerial vehicle, the embodiment constructs a full-connection graph based on the candidate viewpoint set and the optimized viewpoint set, generates an unmanned aerial vehicle flight path of all viewpoints connected in series, and obtains a path traversing all nodes and having the minimum cost by solving the problem of a traveling company. In this embodiment, the nodes in the candidate viewpoint set and the optimized viewpoint set are used as nodes in the graph to construct a full-connection graph, and a method for solving the problem of the traveling salesman is adopted to solve the minimum cost path of the full-connection graph.
Connection viewpoint pair in full connection diagramCost value of edge of (2)The definition is as follows:
,
Wherein, Representing the point of viewTo the point of viewAt the shortest straight-line distance of the safety zone,Representative ofAndIs arranged at the angle of the line of sight direction,Representing the weight value. The path with the minimum cost of the full connection diagram is the optimal unmanned aerial vehicle shooting path for traversing all the viewpoints.
The scene reconstruction step includes a structured geometric reconstruction and a texture reconstruction. And acquiring photos based on the generated unmanned aerial vehicle shooting path, and reconstructing the geometry and texture of the scene. In the geometric reconstruction step, first a high-precision dense geometric model is reconstructed based on the acquired photographs using ContextCapture (context capture) software. Secondly, a structural perception reconstruction algorithm is adopted to obtain a structured model of the dense geometric model. Finally, a TwinTex method (a geometric sense texture generation method of an abstract three-dimensional building model) is used to generate a high-quality texture map for the structured model, as shown in fig. 7.
The method has the advantages that (1) when the image materials acquired by the unmanned aerial vehicle shooting paths obtained by the method are used for texture mapping of the structural model, the view angles corresponding to the same building elevation are more consistent and opposite to planes, so that textures with consistent perspective and opposite view angles can be generated when the acquired image materials are used for texture mapping of the structural model, (2) the view points corresponding to the building elevation have the characteristic of high definition, so that the acquired image materials can be used for texture mapping, and (3) the generated textures have less splicing marks, blurring and deformation.
Based on the above embodiment, the present invention further provides an unmanned aerial vehicle path planning apparatus, as shown in fig. 8, where the apparatus includes:
the data acquisition module 01 is used for acquiring a two-dimensional base map and a safe flight height of a target scene, and determining a candidate view point set according to the two-dimensional base map and the safe flight height;
The viewpoint generating module 02 is configured to generate an initial viewpoint set according to the candidate viewpoint set based on a plane quality and a viewpoint plane pair quality, where the plane quality is used to measure texture quality of a single plane, and the viewpoint plane pair quality is used to measure quality of a viewpoint plane pair constructed by a single viewpoint and a plane;
the viewpoint optimizing module 03 is used for optimizing the initial viewpoint set by adopting a multi-objective optimizing algorithm and determining an optimized viewpoint set;
And the path determining module 04 is used for determining the unmanned aerial vehicle shooting path according to the candidate viewpoint set and the optimized viewpoint set.
Based on the above embodiment, the present invention also provides a terminal, and a functional block diagram thereof may be shown in fig. 9. The terminal comprises a processor, a memory, a network interface and a display screen which are connected through a system bus. Wherein the processor of the terminal is adapted to provide computing and control capabilities. The memory of the terminal includes a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface of the terminal is used for communicating with an external terminal through a network connection. The computer program when executed by the processor is to implement a drone path planning method. The display screen of the terminal may be a liquid crystal display screen or an electronic ink display screen.
It will be appreciated by those skilled in the art that the functional block diagram shown in fig. 9 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the terminal to which the present inventive arrangements may be applied, and that a particular terminal may include more or less components than those shown, or may combine some of the components, or have a different arrangement of components.
In one implementation, the memory of the terminal has stored therein one or more programs, and the execution of the one or more programs by one or more processors includes instructions for performing a drone path planning method.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (SYNCHLINK) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
In summary, the invention discloses a method, a device, a terminal and a storage medium for planning a path of an unmanned aerial vehicle, wherein the method determines a candidate view point set according to a two-dimensional base map and a safe flight height by acquiring the two-dimensional base map and the safe flight height of a target scene; generating an initial viewpoint set according to a candidate viewpoint set based on plane quality and viewpoint plane pair quality, wherein the plane quality is used for measuring texture quality of a single plane, the viewpoint plane pair quality is used for measuring quality of viewpoint plane pairs constructed by the single viewpoint and the plane, optimizing the initial viewpoint set by adopting a multi-objective optimization algorithm to determine an optimized viewpoint set, and determining an unmanned aerial vehicle shooting path according to the candidate viewpoint set and the optimized viewpoint set. According to the invention, the view point set capable of reconstructing high-quality textures is obtained by introducing the plane quality and the view point plane quality, so that the problem that the prior art does not consider how to acquire high-quality image data for texture reconstruction, and the acquired image data cannot achieve an ideal texture effect when used for texture mapping is effectively solved.
It is to be understood that the invention is not limited in its application to the examples described above, but is capable of modification and variation in light of the above teachings by those skilled in the art, and that all such modifications and variations are intended to be included within the scope of the appended claims.

Claims (8)

1.一种无人机路径规划方法，其特征在于，所述方法包括：1. A method for unmanned aerial vehicle path planning, characterized in that the method comprises: 获取目标场景的二维底图和安全飞行高度，根据所述二维底图和所述安全飞行高度确定候选视点集；Acquire a two-dimensional base map and a safe flight altitude of a target scene, and determine a candidate viewpoint set according to the two-dimensional base map and the safe flight altitude; 基于平面质量和视点平面对质量，根据所述候选视点集生成初始视点集，其中，所述平面质量用于衡量单个平面的纹理质量，所述视点平面对质量用于衡量单个视点与平面所构建的视点平面对的质量；Based on the plane quality and the viewpoint-plane pair quality, an initial viewpoint set is generated according to the candidate viewpoint set, wherein the plane quality is used to measure the texture quality of a single plane, and the viewpoint-plane pair quality is used to measure the quality of a viewpoint-plane pair constructed by a single viewpoint and a plane; 采用多目标优化算法对所述初始视点集进行优化，确定优化视点集；Using a multi-objective optimization algorithm to optimize the initial viewpoint set to determine an optimized viewpoint set; 根据所述候选视点集和所述优化视点集确定无人机拍摄路径；Determine a drone shooting path according to the candidate viewpoint set and the optimized viewpoint set; 所述平面质量的计算方法包括：The calculation method of the plane quality includes: ， , 其中，和分别表示透视质量和图像质量，和为权重；in, and Represent the perspective quality and image quality respectively, and is the weight; 透视质量定义为：Perspective quality Defined as: ， , 其中，和为权重，是视点集中视点的数量，衡量单位向量和之间的距离，表示中视点的视线方向，表示中视点的平均视线方向，表示平面的法向量；in, and is the weight, is the viewpoint set The number of viewpoints, Metric Unit Vector and The distance between express Middle Viewpoint The direction of sight, express The average viewing direction of the midpoint, Representation plane The normal vector of 图像质量定义为：Image Quality Defined as: ， , 其中，和为权重，代表视线距离归一化后的值，表示的视线距离，表示中视点的视线距离的平均值，，代表中视点覆盖平面的区域宽度，代表的宽度；in, and is the weight, Represents line of sight distance The normalized value, express The sight distance, express The average value of the sight distance of the midpoint, , represent Mid-viewpoint coverage plane The width of the area, represent Width; 所述视点平面对质量的计算方法包括：The method for calculating the viewpoint plane pair quality includes: ， , 其中，和分别表示透视质量和图像质量，和为权重；in, and Represent the perspective quality and image quality respectively, and is the weight; 透视质量定义为：Perspective quality Defined as: ， , 和为权重，衡量单位向量和之间的距离，表示视点的视线方向，表示视点集中视点的平均视线方向，表示平面的法向量； and is the weight, Metric Unit Vector and The distance between Indicates viewpoint The direction of sight, Represents a viewpoint set The average viewing direction of the midpoint, Representation plane The normal vector of 图像质量定义为：Image Quality Defined as: ， , 和为权重，代表视线距离归一化后的值，表示视点的视线距离，，代表中视点覆盖平面的区域宽度，代表平面的宽度，代表平面中仅被视点观测到的区域的占比。 and is the weight, Represents line of sight distance The normalized value, Indicates viewpoint The sight distance, , represent Mid-viewpoint coverage plane The width of the area, Representative plane The width of Representative plane Only the viewpoint The proportion of the area where the observations were made. 2.根据权利要求1所述的无人机路径规划方法，其特征在于，所述基于平面质量和视点平面对质量，根据所述候选视点集生成初始视点集，包括：2. The method for UAV path planning according to claim 1, characterized in that the generating of the initial viewpoint set according to the candidate viewpoint set based on the plane quality and the viewpoint plane pair quality comprises: 基于所述候选视点集构建若干视点平面对；Constructing a plurality of viewpoint plane pairs based on the candidate viewpoint set; 基于所述平面质量对各所述视点平面对中的视点设置初始视线方向；Setting an initial sight direction for a viewpoint in each of the viewpoint plane pairs based on the plane quality; 计算各所述视点平面对对应的所述视点平面对质量，根据各所述视点平面对质量确定所述初始视点集。The viewpoint-plane pair quality corresponding to each of the viewpoint-plane pairs is calculated, and the initial viewpoint set is determined according to the viewpoint-plane pair quality. 3.根据权利要求2所述的无人机路径规划方法，其特征在于，所述基于所述平面质量对各所述视点平面对中的视点设置初始视线方向，包括：3. The method for UAV path planning according to claim 2, characterized in that the step of setting an initial sight line direction for each viewpoint in each viewpoint plane pair based on the plane quality comprises: 在所述视点平面对中平面法线方向的逆方向为中心的180°范围内采样，确定若干候选视线方向；Sampling within a 180° range centered on the reverse direction of the normal direction of the midpoint plane to determine a number of candidate sight lines; 选取所述平面质量最大时对应的所述候选视线方向为所述视点平面对中视点的所述初始视线方向。The candidate sight line direction corresponding to the maximum plane quality is selected as the initial sight line direction of the viewpoint centered on the viewpoint plane. 4.根据权利要求1所述的无人机路径规划方法，其特征在于，所述采用多目标优化算法对所述初始视点集进行优化，确定优化视点集，包括：4. The UAV path planning method according to claim 1, characterized in that the use of a multi-objective optimization algorithm to optimize the initial viewpoint set to determine the optimized viewpoint set comprises: 在所述初始视点集中的每一视点的邻域范围内进行位置和视线方向的采样，得到各视点对应的候选视点位姿；Sampling the position and sight direction of each viewpoint in the neighborhood of the initial viewpoint set to obtain candidate viewpoint poses corresponding to each viewpoint; 基于多目标优化算法确定所述候选视点位姿中的目标视点位姿；Determine a target viewpoint pose among the candidate viewpoint poses based on a multi-objective optimization algorithm; 根据各视点对应的所述目标视点位姿对所述初始视点集进行筛选，确定所述优化视点集。The initial viewpoint set is screened according to the target viewpoint pose corresponding to each viewpoint to determine the optimized viewpoint set. 5.根据权利要求1所述的无人机路径规划方法，其特征在于，所述根据所述候选视点集和所述优化视点集确定无人机拍摄路径，包括：5. The method for drone path planning according to claim 1, wherein determining the drone shooting path according to the candidate viewpoint set and the optimized viewpoint set comprises: 根据所述候选视点集和所述优化视点集构建全连接图；Constructing a fully connected graph according to the candidate viewpoint set and the optimized viewpoint set; 基于旅行商问题求解所述全连接图对应的代价最小路径作为所述无人机拍摄路径。The minimum cost path corresponding to the fully connected graph is solved based on the traveling salesman problem as the drone shooting path. 6.一种无人机路径规划装置，其特征在于，所述装置包括：6. A drone path planning device, characterized in that the device comprises: 数据获取模块，用于获取目标场景的二维底图和安全飞行高度，根据所述二维底图和所述安全飞行高度确定候选视点集；A data acquisition module, used to acquire a two-dimensional base map and a safe flight altitude of a target scene, and determine a candidate viewpoint set according to the two-dimensional base map and the safe flight altitude; 视点生成模块，用于基于平面质量和视点平面对质量，根据所述候选视点集生成初始视点集，其中，所述平面质量用于衡量单个平面的纹理质量，所述视点平面对质量用于衡量单个视点与平面所构建的视点平面对的质量；A viewpoint generation module, configured to generate an initial viewpoint set according to the candidate viewpoint set based on a plane quality and a viewpoint-plane pair quality, wherein the plane quality is used to measure the texture quality of a single plane, and the viewpoint-plane pair quality is used to measure the quality of a viewpoint-plane pair constructed by a single viewpoint and a plane; 视点优化模块，用于采用多目标优化算法对所述初始视点集进行优化，确定优化视点集；A viewpoint optimization module, used to optimize the initial viewpoint set using a multi-objective optimization algorithm to determine an optimized viewpoint set; 路径确定模块，用于根据所述候选视点集和所述优化视点集确定无人机拍摄路径；A path determination module, used to determine a drone shooting path according to the candidate viewpoint set and the optimized viewpoint set; 所述平面质量的计算方法包括：The calculation method of the plane quality includes: ， , 其中，和分别表示透视质量和图像质量，和为权重；in, and Represent the perspective quality and image quality respectively, and is the weight; 透视质量定义为：Perspective quality Defined as: ， , 其中，和为权重，是视点集中视点的数量，衡量单位向量和之间的距离，表示中视点的视线方向，表示中视点的平均视线方向，表示平面的法向量；in, and is the weight, is the viewpoint set The number of viewpoints, Metric Unit Vector and The distance between express Middle Viewpoint The direction of sight, express The average viewing direction of the midpoint, Representation plane The normal vector of 图像质量定义为：Image Quality Defined as: ， , 其中，和为权重，代表视线距离归一化后的值，表示的视线距离，表示中视点的视线距离的平均值，，代表中视点覆盖平面的区域宽度，代表的宽度；in, and is the weight, Represents line of sight distance The normalized value, express The sight distance, express The average value of the sight distance of the midpoint, , represent Mid-viewpoint coverage plane The width of the area, represent Width; 所述视点平面对质量的计算方法包括：The method for calculating the viewpoint plane pair quality includes: ， , 其中，和分别表示透视质量和图像质量，和为权重；in, and Represent the perspective quality and image quality respectively, and is the weight; 透视质量定义为：Perspective quality Defined as: ， , 和为权重，衡量单位向量和之间的距离，表示视点的视线方向，表示视点集中视点的平均视线方向，表示平面的法向量； and is the weight, Metric Unit Vector and The distance between Indicates viewpoint The direction of sight, Represents a viewpoint set The average viewing direction of the midpoint, Representation plane The normal vector of 图像质量定义为：Image Quality Defined as: ， , 和为权重，代表视线距离归一化后的值，表示视点的视线距离，，代表中视点覆盖平面的区域宽度，代表平面的宽度，代表平面中仅被视点观测到的区域的占比。 and is the weight, Represents line of sight distance The normalized value, Indicates viewpoint The sight distance, , represent Mid-viewpoint coverage plane The width of the area, Representative plane The width of Representative plane Only the viewpoint The proportion of the area where the observations were made. 7.一种终端，其特征在于，所述终端包括有存储器和一个以上处理器；所述存储器存储有一个以上的程序；所述程序包含用于执行如权利要求1-5中任一所述的无人机路径规划方法的指令；所述处理器用于执行所述程序。7. A terminal, characterized in that the terminal includes a memory and one or more processors; the memory stores one or more programs; the program contains instructions for executing the drone path planning method as described in any one of claims 1-5; and the processor is used to execute the program. 8.一种计算机可读存储介质，其上存储有多条指令，其特征在于，所述指令适用于由处理器加载并执行，以实现上述权利要求1-5任一所述的无人机路径规划方法的步骤。8. A computer-readable storage medium having a plurality of instructions stored thereon, wherein the instructions are suitable for being loaded and executed by a processor to implement the steps of the drone path planning method described in any one of claims 1 to 5.
CN202411312008.1A 2024-09-20 2024-09-20 Unmanned aerial vehicle path planning method, unmanned aerial vehicle path planning device, terminal and storage medium Active CN118816899B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202411312008.1A CN118816899B (en) 2024-09-20 2024-09-20 Unmanned aerial vehicle path planning method, unmanned aerial vehicle path planning device, terminal and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202411312008.1A CN118816899B (en) 2024-09-20 2024-09-20 Unmanned aerial vehicle path planning method, unmanned aerial vehicle path planning device, terminal and storage medium

Publications (2)

Publication Number Publication Date
CN118816899A CN118816899A (en) 2024-10-22
CN118816899B true CN118816899B (en) 2024-12-17

Family

ID=93085703

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202411312008.1A Active CN118816899B (en) 2024-09-20 2024-09-20 Unmanned aerial vehicle path planning method, unmanned aerial vehicle path planning device, terminal and storage medium

Country Status (1)

Country Link
CN (1) CN118816899B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119540453B (en) * 2024-11-11 2025-09-19 中国人民解放军国防科技大学 A UAV trajectory planning method for visual 3D reconstruction of urban scenes

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115979273A (en) * 2023-01-28 2023-04-18 西安交通大学 UAV full coverage path planning method and system based on adaptive viewpoint sampling
CN117970951A (en) * 2023-12-05 2024-05-03 深圳大学 Unmanned aerial vehicle modeling three-dimensional route planning method, terminal and storage medium

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108318046B (en) * 2017-01-18 2020-12-15 华为技术有限公司 Path planning method and device

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115979273A (en) * 2023-01-28 2023-04-18 西安交通大学 UAV full coverage path planning method and system based on adaptive viewpoint sampling
CN117970951A (en) * 2023-12-05 2024-05-03 深圳大学 Unmanned aerial vehicle modeling three-dimensional route planning method, terminal and storage medium

Also Published As

Publication number Publication date
CN118816899A (en) 2024-10-22

Similar Documents

Publication Publication Date Title
CN116129020A (en) Novel live-action three-dimensional modeling method
CN113393577B (en) Oblique photography terrain reconstruction method
CN118816899B (en) Unmanned aerial vehicle path planning method, unmanned aerial vehicle path planning device, terminal and storage medium
CN103310487B (en) A kind of universal imaging geometric model based on time variable generates method
CN113920275B (en) Triangular mesh construction method and device, electronic equipment and readable storage medium
CN110046563B (en) Power transmission line section elevation correction method based on unmanned aerial vehicle point cloud
JP2021012078A (en) Temperature distribution estimation device and temperature distribution estimation method
CN115294280A (en) Three-dimensional reconstruction method, apparatus, device, storage medium, and program product
CN118864234B (en) Method, apparatus and program product for generating three-dimensional curved surface in geometric engine, and medium
CN116894870B (en) Image target positioning method, system, electronic device and storage medium
CN116109706B (en) Space target inversion method, device and equipment based on prior geometric constraints
CN116310756B (en) Remains identification method, remains identification device, electronic equipment and computer storage medium
CN116972880A (en) Precision detection device of positioning algorithm
Ma et al. Low‐Altitude Photogrammetry and Remote Sensing in UAV for Improving Mapping Accuracy
CN106530342B (en) Full-view image generation method is measured using what laser point cloud was aided in
CN115100286B (en) Method, device, computer equipment and storage medium for determining viewpoint of drone collection
CN115421509B (en) Unmanned aerial vehicle flight shooting planning method, unmanned aerial vehicle flight shooting planning device and storage medium
CN115775351A (en) A multi-task parallel processing method for aerial image orthorectification
CN115239784A (en) Point cloud generation method and device, computer equipment and storage medium
CN118837886B (en) Spatial target axial estimation method, device, computer equipment and storage medium
Ebrahimikia et al. Orthophoto improvement using urban-SnowflakeNet
CN117235299A (en) Quick indexing method, system, equipment and medium for oblique photographic pictures
CN116863137A (en) Optimization method, device and computer equipment for three-dimensional model of transmission tower
JP2020041950A (en) Surveying device, surveying method, and program
Zaman et al. Effects of UAV imagery overlap on photogrammetric data quality for construction applications

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