CN118050007A - Unmanned aerial vehicle navigation system and method based on image recognition - Google Patents
Unmanned aerial vehicle navigation system and method based on image recognition Download PDFInfo
- Publication number
- CN118050007A CN118050007A CN202410453274.XA CN202410453274A CN118050007A CN 118050007 A CN118050007 A CN 118050007A CN 202410453274 A CN202410453274 A CN 202410453274A CN 118050007 A CN118050007 A CN 118050007A
- Authority
- CN
- China
- Prior art keywords
- identification
- shooting
- unmanned aerial
- aerial vehicle
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 63
- 230000005856 abnormality Effects 0.000 claims abstract description 17
- 238000012790 confirmation Methods 0.000 claims abstract description 16
- 230000002159 abnormal effect Effects 0.000 claims abstract description 12
- 238000004458 analytical method Methods 0.000 claims description 19
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 238000012937 correction Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 239000002131 composite material Substances 0.000 claims description 2
- 238000012876 topography Methods 0.000 claims description 2
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 abstract description 7
- 238000010586 diagram Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Landscapes
- Navigation (AREA)
Abstract
The embodiment of the invention relates to the technical field of unmanned aerial vehicle navigation, and particularly discloses an unmanned aerial vehicle navigation system and method based on image recognition. According to the embodiment of the invention, unmanned aerial vehicle navigation planning is carried out on the target unmanned aerial vehicle, and a plurality of navigation passing marks are selected; planning a plurality of identification shooting positions and a plurality of shooting gesture data; in the flying process of the unmanned aerial vehicle, shooting is carried out at a plurality of mark shooting positions according to a plurality of shooting gesture data, and a plurality of mark shooting data are obtained; and comparing and identifying the plurality of identification shooting data according to the plurality of identification appearance data, and confirming a route or alarming abnormality according to a comparison and identification result. The navigation system can select a plurality of navigation passing marks, plan a plurality of mark shooting positions and a plurality of shooting gesture data, carry out shooting control and comparison identification in the flight process of the unmanned aerial vehicle, and carry out route confirmation or abnormal alarm according to comparison identification results, thereby ensuring that the navigation system is in a region with poor signals and inaccurate positioning, and improving the accuracy and the qualitability of flight control.
Description
Technical Field
The invention belongs to the technical field of unmanned aerial vehicle navigation, and particularly relates to an unmanned aerial vehicle navigation system and method based on image recognition.
Background
Unmanned aerial vehicle navigation refers to the process that unmanned aerial vehicle autonomously determines the space position, speed, gesture and course in the process of executing the flight task, so that unmanned aerial vehicle can accurately fly on a preset route and complete various complex tasks.
Unmanned aerial vehicle navigation mainly involves a variety of techniques to ensure that unmanned aerial vehicle can fly according to a preset route, including: global positioning system, inertial navigation system, electronic compass, path planning and path tracking technology, etc.
In the prior art, after the navigation of the flight route of the unmanned aerial vehicle is finished, the flight control of the unmanned aerial vehicle is directly carried out according to the navigation route, but in some areas with poor signals and inaccurate positioning, the accurate flight control is difficult to carry out according to the navigation.
Disclosure of Invention
The embodiment of the invention aims to provide an unmanned aerial vehicle navigation system and method based on image recognition, and aims to solve the problems in the background technology.
In order to achieve the above object, the embodiment of the present invention provides the following technical solutions:
An unmanned aerial vehicle navigation method based on image recognition, which specifically comprises the following steps:
performing unmanned aerial vehicle navigation planning on a target unmanned aerial vehicle, acquiring an unmanned aerial vehicle navigation route, analyzing the unmanned aerial vehicle navigation route, and selecting a plurality of navigation passing identifiers;
acquiring a plurality of pieces of identification position data and a plurality of pieces of identification shape data of the navigation passing through the identification, and planning a plurality of pieces of identification shooting positions and a plurality of pieces of shooting gesture data according to the plurality of pieces of identification position data;
shooting the unmanned aerial vehicle according to a plurality of shooting gesture data at a plurality of mark shooting positions in the flying process of the unmanned aerial vehicle according to the unmanned aerial vehicle navigation route, and obtaining a plurality of mark shooting data;
And comparing and identifying the plurality of the identification shooting data according to the plurality of the identification appearance data, and confirming a route or alarming abnormality according to a comparison and identification result.
As a further limitation of the technical solution of the embodiment of the present invention, the unmanned aerial vehicle navigation planning is performed on the target unmanned aerial vehicle, the unmanned aerial vehicle navigation route is obtained, the unmanned aerial vehicle navigation route is analyzed, and the selecting a plurality of navigation passing identifiers specifically includes the following steps:
Acquiring a flight destination position;
selecting a target unmanned aerial vehicle according to the flight target position, and acquiring a target initial position;
According to the target initial position and the flight destination position, unmanned aerial vehicle navigation planning is carried out, and an unmanned aerial vehicle navigation route is obtained;
And carrying out identification analysis on the navigation route of the unmanned aerial vehicle, and selecting a plurality of navigation passing identifications.
As a further limitation of the technical solution of the embodiment of the present invention, selecting a target unmanned aerial vehicle according to the flight destination position, and obtaining the target initial position specifically includes the following steps:
Determining a plurality of idle unmanned aerial vehicles;
Acquiring idle initial positions of a plurality of idle unmanned aerial vehicles;
Calculating flight distances between the idle initial positions and the flight destination positions;
comparing a plurality of flight distances, and marking the idle initial position with the shortest flight distance as a target initial position;
and selecting the target unmanned aerial vehicle according to the target initial position.
As a further limitation of the technical solution of the embodiment of the present invention, the acquiring a plurality of identified position data and a plurality of identified shape data of the navigation identified, and planning a plurality of identified shooting positions and a plurality of shooting gesture data according to a plurality of identified position data specifically includes the following steps:
acquiring a plurality of pieces of identification appearance data of a plurality of the navigation identifications;
Acquiring a plurality of pieces of identification position data of the navigation identified;
selecting a plurality of mark shooting positions from the unmanned aerial vehicle navigation route according to a plurality of mark position data;
and relatively analyzing the plurality of identification shooting positions and the plurality of identification position data, and planning a plurality of shooting gesture data.
As a further limitation of the technical solution of the embodiment of the present invention, in the process of flying the unmanned aerial vehicle according to the navigation route of the unmanned aerial vehicle, shooting is performed at a plurality of mark shooting positions according to a plurality of shooting gesture data, and the step of obtaining a plurality of mark shooting data specifically includes the following steps:
Carrying out real-time positioning analysis on the unmanned aerial vehicle in the flying process according to the navigation route of the unmanned aerial vehicle;
generating a plurality of shooting control signals according to a plurality of shooting gesture data;
at a plurality of the identification shooting positions, respectively sending a plurality of shooting control signals to the target unmanned aerial vehicle;
and acquiring a plurality of identification shooting data transmitted by the feedback of the target unmanned aerial vehicle.
As a further limitation of the technical solution of the embodiment of the present invention, the comparing and identifying the plurality of the identification shooting data according to the plurality of the identification appearance data, and performing route confirmation or abnormality alarm according to the comparing and identifying result specifically includes the following steps:
Extracting identification appearance characteristics of a plurality of identification appearance data;
according to the appearance characteristics of the marks, comparing and identifying the shooting data of the marks to obtain a plurality of comparison and identification results;
when the comparison and identification results are successful, confirming the route;
And when at least one comparison and identification result is that the comparison and identification is failed, carrying out abnormal alarm.
An unmanned aerial vehicle navigation system based on image recognition, the system includes navigation mark selection unit, mark shooting planning unit, mark shooting control unit and image contrast recognition unit, wherein:
The navigation mark selection unit is used for carrying out unmanned aerial vehicle navigation planning on a target unmanned aerial vehicle, acquiring an unmanned aerial vehicle navigation route, analyzing the unmanned aerial vehicle navigation route and selecting a plurality of navigation passing marks;
The mark shooting planning unit is used for acquiring a plurality of mark position data and a plurality of mark appearance data of the navigation mark, and planning a plurality of mark shooting positions and a plurality of shooting gesture data according to the plurality of mark position data;
The mark shooting control unit is used for shooting at a plurality of mark shooting positions according to a plurality of shooting gesture data in the flying process of the unmanned aerial vehicle according to the unmanned aerial vehicle navigation route, so as to obtain a plurality of mark shooting data;
And the image comparison and identification unit is used for comparing and identifying the plurality of the identification shooting data according to the plurality of the identification appearance data and carrying out route confirmation or abnormal alarm according to the comparison and identification result.
As a further limitation of the technical solution of the embodiment of the present invention, the navigation identifier selecting unit specifically includes:
the target position acquisition module is used for acquiring a flight target position;
The initial position acquisition module is used for selecting a target unmanned aerial vehicle according to the flight target position and acquiring a target initial position;
The navigation planning module is used for carrying out unmanned aerial vehicle navigation planning according to the target initial position and the flight destination position, and obtaining an unmanned aerial vehicle navigation route;
the identification selection module is used for carrying out identification analysis on the unmanned aerial vehicle navigation route and selecting a plurality of navigation passing identifications.
As a further limitation of the technical solution of the embodiment of the present invention, the identification shooting planning unit specifically includes:
The appearance data acquisition module is used for acquiring a plurality of pieces of identification appearance data of the navigation identified;
the position data acquisition module is used for acquiring a plurality of pieces of marked position data of the navigation marked;
The shooting position selection module is used for selecting a plurality of identification shooting positions from the unmanned aerial vehicle navigation route according to a plurality of identification position data;
And the gesture data planning module is used for carrying out relative analysis on the plurality of the identification shooting positions and the plurality of the identification position data and planning a plurality of shooting gesture data.
As a further limitation of the technical solution of the embodiment of the present invention, the image comparison and identification unit specifically includes:
The feature extraction module is used for extracting the identification appearance features of a plurality of identification appearance data;
the comparison and identification module is used for comparing and identifying the plurality of the identification shooting data according to the appearance characteristics of the plurality of the identifications and obtaining a plurality of comparison and identification results;
the route confirmation module is used for confirming the route when the comparison and identification results are successful;
And the abnormality alarm module is used for carrying out abnormality alarm when at least one comparison and identification result is that the comparison and identification fails.
Compared with the prior art, the invention has the beneficial effects that:
According to the embodiment of the invention, unmanned aerial vehicle navigation planning is carried out on the target unmanned aerial vehicle, and a plurality of navigation passing marks are selected; planning a plurality of identification shooting positions and a plurality of shooting gesture data; in the flying process of the unmanned aerial vehicle, shooting is carried out at a plurality of mark shooting positions according to a plurality of shooting gesture data, and a plurality of mark shooting data are obtained; and comparing and identifying the plurality of identification shooting data according to the plurality of identification appearance data, and confirming a route or alarming abnormality according to a comparison and identification result. The navigation system can select a plurality of navigation passing marks, plan a plurality of mark shooting positions and a plurality of shooting gesture data, carry out shooting control and comparison identification in the flight process of the unmanned aerial vehicle, and carry out route confirmation or abnormal alarm according to comparison identification results, thereby ensuring that the navigation system is in a region with poor signals and inaccurate positioning, and improving the accuracy and the qualitability of flight control.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following description will briefly introduce the drawings that are needed in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the present invention.
Fig. 1 shows a flowchart of a method provided by an embodiment of the present invention.
FIG. 2 illustrates a flow chart of selecting a plurality of navigation pass-through identifiers in a method provided by an embodiment of the invention.
Fig. 3 shows a flowchart of acquiring an initial position of a target in the method provided by the embodiment of the invention.
Fig. 4 shows a flowchart for planning a plurality of identified shooting locations and a plurality of shooting pose data in a method according to an embodiment of the present invention.
Fig. 5 shows a flowchart of acquiring a plurality of identification shooting data in the method provided by the embodiment of the invention.
FIG. 6 shows a flow chart of a route validation or anomaly alarm in a method provided by an embodiment of the invention.
Fig. 7 shows an application architecture diagram of a system provided by an embodiment of the present invention.
Fig. 8 is a block diagram of a navigation mark selecting unit in the system according to the embodiment of the present invention.
Fig. 9 shows a block diagram of a system according to an embodiment of the present invention.
Fig. 10 is a block diagram showing the structure of an image comparison and identification unit in the system according to the embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
It can be appreciated that in the prior art, after the navigation of the flight path of the unmanned aerial vehicle is completed, the flight control of the unmanned aerial vehicle is directly performed according to the navigation path. However, in some areas where signals are poor and positioning is inaccurate, it is difficult to perform accurate flight control according to navigation.
In order to solve the problems, according to the embodiment of the invention, unmanned aerial vehicle navigation planning is performed on a target unmanned aerial vehicle, an unmanned aerial vehicle navigation route is obtained, the unmanned aerial vehicle navigation route is analyzed, and a plurality of navigation passing identifiers are selected; acquiring a plurality of pieces of identification position data and a plurality of pieces of identification shape data of the navigation passing through the identification, and planning a plurality of pieces of identification shooting positions and a plurality of pieces of shooting gesture data according to the plurality of pieces of identification position data; shooting according to the shooting gesture data at a plurality of mark shooting positions in the flying process of the unmanned aerial vehicle according to the navigation route of the unmanned aerial vehicle, and obtaining a plurality of mark shooting data; and comparing and identifying the plurality of identification shooting data according to the plurality of identification appearance data, and confirming a route or alarming abnormality according to a comparison and identification result. The navigation system can select a plurality of navigation pass marks, plan a plurality of mark shooting positions and a plurality of shooting gesture data, carry out shooting control and comparison identification in the flight process of the unmanned aerial vehicle, and carry out route confirmation or abnormal alarm according to comparison identification results, thereby ensuring that accurate flight control can still be carried out in areas with poor signals and inaccurate positioning.
Fig. 1 shows a flowchart of a method provided by an embodiment of the present invention.
Specifically, an unmanned aerial vehicle navigation method based on image recognition, the method specifically includes the following steps:
step S101, unmanned aerial vehicle navigation planning is carried out on a target unmanned aerial vehicle, an unmanned aerial vehicle navigation route is obtained, analysis is carried out on the unmanned aerial vehicle navigation route, and a plurality of navigation passing identifiers are selected.
In the embodiment of the invention, the flight destination position is obtained, a plurality of idle unmanned aerial vehicles in an idle state at the moment are determined, the idle initial positions of the idle unmanned aerial vehicles are obtained, the straight flight distance between the idle initial positions and the flight destination position is calculated, the idle initial positions with the shortest flight distance are marked as the target initial positions by comparing the flight distances, the idle unmanned aerial vehicle corresponding to the target initial positions is marked as the target unmanned aerial vehicle, the flight navigation planning of the unmanned aerial vehicle is carried out between the target initial positions and the flight destination positions, the unmanned aerial vehicle navigation route is obtained, the identification analysis is carried out on the unmanned aerial vehicle navigation route, and the navigation passing identifications are selected. Wherein the plurality of navigation pass through markers can be buildings, plants, roads and the like.
Specifically, fig. 2 illustrates a flowchart of selecting a plurality of navigation pass identifiers in a method provided by an embodiment of the present invention.
In a preferred embodiment of the present invention, the unmanned aerial vehicle navigation planning is performed on the target unmanned aerial vehicle, the unmanned aerial vehicle navigation route is obtained, the unmanned aerial vehicle navigation route is analyzed, and the selecting a plurality of navigation passing identifiers specifically includes the following steps:
step S1011, a flight destination position is acquired.
Step S1012, selecting a target unmanned aerial vehicle according to the flight destination position, and acquiring a target initial position.
Specifically, fig. 3 shows a flowchart of acquiring an initial position of a target in the method provided by the embodiment of the invention.
In the preferred embodiment of the present invention, selecting a target unmanned aerial vehicle according to the flight destination position, and acquiring a target initial position specifically includes the following steps:
step S10121, determining a plurality of idle unmanned aerial vehicles;
Step S10122, acquiring a plurality of idle initial positions of the idle unmanned aerial vehicle;
Step S10123, calculating the flight distances between a plurality of idle initial positions and the flight destination position;
wherein, step S10123 comprises the following sub-steps:
step S10123a, obtaining latitude and longitude corresponding to the idle initial position and latitude and longitude of the flight destination position;
Step S10123b, respectively calculating a latitude difference value and a longitude difference value between the idle initial position and the flight destination position according to the latitude and the longitude corresponding to the idle initial position and the latitude and the longitude of the flight destination position;
Step S10123c, calculating the flight distance between the idle initial position and the flight destination position according to the latitude difference value and the longitude difference value between the idle initial position and the flight destination position;
The calculation formula of the flight distance between the idle initial position and the flight destination position is expressed as follows:
wherein, Representing the flight distance of the idle initial position and the flight destination position,/>Representing the earth radius,/>Representing the difference in altitude between the idle initial position and the destination position,/>Representing the difference in longitude between the free initial position and the destination position,/>Latitude representing the free initial position,/>Latitude indicating the destination of the flight,/>Correction factor representing latitude term,/>A correction factor representing a longitude term.
Step S10124, comparing a plurality of flight distances, and marking the idle initial position with the shortest flight distance as a target initial position;
step S10125, selecting a target unmanned aerial vehicle according to the target initial position.
Further, the unmanned aerial vehicle navigation planning is performed on the target unmanned aerial vehicle, the unmanned aerial vehicle navigation route is obtained, the unmanned aerial vehicle navigation route is analyzed, and the selection of a plurality of navigation pass identifiers further comprises the following steps:
step S1013, performing unmanned aerial vehicle navigation planning according to the target initial position and the flight destination position, and obtaining an unmanned aerial vehicle navigation route.
Step S1013 includes the following sub-steps:
Step S10131, determining the target initial position and the flight destination position, and acquiring surrounding environment data, wherein the surrounding environment data comprises flight topography data, obstacle data and meteorological condition data;
Step S10132, calculating a preferred planning route between the target initial position and the flight destination position by utilizing a routing algorithm based on the target initial position and the flight destination position and combining the collected surrounding environment data;
In the invention, the cost function corresponding to the routing algorithm comprises a flight distance cost, a terrain threat cost and a radar threat cost. The formula of the cost function corresponding to the routing algorithm is expressed as:
wherein, Representing the total cost of the cost function corresponding to the routing algorithm,/>Represents the/>Terrain threat cost of segment,/>Represents the/>Radar threat cost of segment,/>Represents the/>Flight distance cost of segment,/>Weight coefficient representing terrain threat item,/>Weight coefficient representing radar threat item,/>Weight coefficient representing flight distance item,/>Representing the number of segments into which the route is divided.
Wherein the total cost function of the terrain threat is expressed as:
wherein, Representing the total cost of the terrain threat for the entire route;
The total cost function of flight distance is expressed as:
wherein, Total cost function representing flight distance,/>Representing a dot/>To the point/>Is used for the distance of (a),Representing the total number of points on the route;
The total cost function of a radar threat is expressed as:
wherein, Representing the total cost function of a radar threat/>Representing the number of radar stations in the vicinity of the route,/>Represents the/>Performance factors of individual radar stations for representing the detection capabilities of the radar station,/>Representation of unmanned plane to the/>Distance of individual radar stations,/>Represents the/>And the detection capability correction factors corresponding to the radar stations. Step S10133, setting navigation parameters of the unmanned aerial vehicle according to the optimal planning route, and adjusting and optimizing the optimal planning route to obtain the unmanned aerial vehicle navigation route.
Among other things, the navigational parameters of the drone include altitude, speed, and heading, which are required to ensure that the drone is able to fly safely and efficiently along the planned route. It can be appreciated that during the flight of the unmanned aerial vehicle, the unmanned aerial vehicle's flight status and changes in the surrounding environment are monitored in real time via the communication link between the unmanned aerial vehicle and the ground control station. If necessary, the flight route can be adjusted in real time to ensure the flight safety.
Step S1014, performing identification analysis on the unmanned aerial vehicle navigation route, and selecting a plurality of navigation passing identifications.
Further, the unmanned aerial vehicle navigation method based on image recognition further comprises the following steps:
Step S102, a plurality of pieces of marked position data and a plurality of pieces of marked appearance data which are marked by navigation are obtained, and a plurality of marked shooting positions and a plurality of pieces of shooting gesture data are planned according to the plurality of pieces of marked position data.
In the embodiment of the invention, based on a big data technology, a plurality of mark appearance data corresponding to a plurality of navigation passing marks are obtained, a plurality of mark position data corresponding to a plurality of navigation passing marks are obtained, a plurality of mark shooting positions are selected from an unmanned aerial vehicle navigation route according to the plurality of mark position data, then relative analysis is carried out on the plurality of mark shooting positions and the plurality of mark position data, a plurality of shooting gesture data are planned, wherein the plurality of shooting gesture data comprise shooting angles, shooting focal lengths, exposure, shutters and the like.
Specifically, fig. 4 shows a flowchart of planning a plurality of identification shooting positions and a plurality of shooting gesture data in the method provided by the embodiment of the invention.
In a preferred embodiment of the present invention, the acquiring a plurality of identified location data and a plurality of identified shape data of the navigation device, and planning a plurality of identified shooting locations and a plurality of shooting gesture data according to a plurality of identified location data specifically includes the following steps:
Step S1021, a plurality of pieces of marked appearance data of the marked navigation are obtained;
step S1022, obtaining a plurality of pieces of identified position data of the navigation identified;
wherein the identification position data comprises coordinates of the identification in three-dimensional space, i.e. a plurality of identification positions per se.
Step S1023, selecting a plurality of mark shooting positions from the unmanned aerial vehicle navigation route according to a plurality of mark position data;
the identification shooting position comprises longitude and latitude of the shooting position, shooting height and shooting direction.
And step S1024, carrying out relative analysis on the plurality of identification shooting positions and the plurality of identification position data, and planning a plurality of shooting gesture data.
Step S1024 includes the following sub-steps:
Step S1024a, determining the position of each mark and the corresponding mark shooting position, and analyzing and calculating the distance and angle between the position of each mark and the mark shooting position;
step S1024b, according to the distance and angle between the position of the mark and the shooting position of the mark, shooting gesture data corresponding to the shooting equipment are calculated and determined, wherein the shooting gesture data comprise a rotation angle and a pitch angle.
Wherein, the formula of calculation of the rotation angle that shooting equipment corresponds is expressed as:
wherein, Representing the corresponding rotation angle of the shooting equipment,/>Respectively represent the direction vector/>/>Component sum/>A component;
Direction vector Direction vector representing the position from the logo shooting position to the logo itself, direction vector/>The calculation formula of (2) is expressed as:
Wherein the coordinates of the position of the mark are Coordinates identifying the shooting position are/>. The calculation formula of the pitch angle corresponding to the shooting equipment is expressed as follows:
wherein, Representing the pitch angle corresponding to the shooting equipment,/>Representing the direction vector/>Projection on horizontal plane,/>。
Further, the unmanned aerial vehicle navigation method based on image recognition further comprises the following steps:
step S103, shooting a plurality of mark shooting positions according to a plurality of shooting gesture data in the flying process of the unmanned aerial vehicle according to the unmanned aerial vehicle navigation route, and obtaining a plurality of mark shooting data.
In the embodiment of the invention, in the process of flying according to the navigation route of the unmanned aerial vehicle, the target unmanned aerial vehicle is positioned in real time to obtain the real-time flying position, and a plurality of corresponding shooting control signals are generated according to a plurality of shooting gesture data, when the real-time flying position is one of a plurality of mark shooting positions, the corresponding shooting control signals are sent to the target unmanned aerial vehicle, the target unmanned aerial vehicle is controlled to shoot the corresponding navigation passing mark, and the mark shooting data are fed back, so that the plurality of mark shooting data can be obtained.
Specifically, fig. 5 shows a flowchart of acquiring a plurality of identification shooting data in the method provided by the embodiment of the invention.
In the preferred embodiment of the present invention, in the flying process of the unmanned aerial vehicle according to the navigation route of the unmanned aerial vehicle, shooting is performed at a plurality of mark shooting positions according to a plurality of shooting gesture data, and the step of obtaining a plurality of mark shooting data specifically includes the following steps:
step S1031, performing real-time positioning analysis on the unmanned aerial vehicle in the flying process according to the navigation route of the unmanned aerial vehicle;
Step S1032, generating a plurality of shooting control signals according to a plurality of shooting attitude data;
step S1033, in a plurality of the identified shooting positions, sending a plurality of the shooting control signals to the target unmanned aerial vehicle respectively;
Step S1034, obtaining a plurality of identification shooting data transmitted by the target unmanned aerial vehicle in a feedback manner.
Further, the unmanned aerial vehicle navigation method based on image recognition further comprises the following steps:
And step S104, comparing and identifying the plurality of the identification shooting data according to the plurality of the identification appearance data, and confirming a route or alarming abnormality according to the comparison and identification result.
In the embodiment of the invention, the characteristic analysis is carried out on the plurality of mark appearance data, the plurality of mark appearance characteristics of appearance, color and the like are extracted, then the comparison and identification are carried out on the plurality of mark shooting data according to the plurality of mark appearance characteristics, a plurality of comparison and identification results are obtained, and the route confirmation or abnormal alarm is carried out according to different comparison and identification results, and the method is specific: when the comparison and identification results are successful, confirming the route, and continuing normal flight; and when at least one comparison and identification result is that the comparison and identification is failed, carrying out abnormal alarm, and then carrying out flight adjustment.
Specifically, fig. 6 shows a flowchart of route confirmation or abnormality alarm in the method provided by the embodiment of the invention.
In a preferred embodiment of the present invention, comparing and identifying the plurality of the identification shooting data according to the plurality of the identification appearance data, and performing route confirmation or abnormality alarm according to the comparison and identification result specifically includes the following steps:
Step S1041, extracting a plurality of identification appearance characteristics of the identification appearance data;
Step S1042, comparing and identifying the plurality of the identification shooting data according to the appearance characteristics of the plurality of the identifications to obtain a plurality of comparison and identification results;
step S1042 includes the following sub-steps:
Step S1042a, according to the plurality of the mark appearance characteristics, performing shape contrast recognition, color contrast recognition, texture contrast recognition and size proportion contrast recognition on the plurality of the mark shooting data to obtain a shape recognition item score, a color recognition item score, a texture recognition item score and a size proportion recognition item score respectively;
The shape comparison recognition means recognition by comparing the similarity between the shape of the mark in the captured data and the shape of the known mark. This may be achieved by calculating the degree of matching between contours, boundaries or keypoints of the shape. The color contrast identification means that if the identification has a specific color or combination of colors, the identification can be performed by comparing the similarity of the color identified in the photographed data with the known identification color. The color contrast may be based on a color histogram, a color moment, or other color features. In texture contrast recognition, the identified surface texture can also be used as an important recognition feature, and effective contrast recognition can be performed by extracting and comparing the identified texture features in the photographed data with the texture features of known identifications. In the size and proportion comparison and identification, the identification is performed by comparing whether the size characteristics such as the size and the length-width ratio of the identification in the shooting data are consistent with the size characteristics of the known identification.
Step S1042b, judging whether the shape recognition item score, the color recognition item score, the texture recognition item score, and the size proportion recognition item score are all greater than the corresponding shape recognition item score threshold, color recognition item score threshold, texture recognition item score threshold, and size proportion recognition item score threshold;
Step S1042c, if yes, calculating an identification comprehensive score for identifying shooting data based on the shape identification item score, the color identification item score, the texture identification item score and the size proportion identification item score;
Wherein, the calculation formula of the identification comprehensive score is expressed as follows:
wherein, Representing the recognition composite score,/>Representing shape recognition item score,/>A color recognition term score is represented and,Representing texture recognition term score,/>Representing size scale recognition term score,/>Weight factor representing shape recognition term,/>Weight factor representing color recognition term,/>Weight factor representing texture recognition term,/>A weight factor representing the size scale identification term.
And step S1042d, when the identification comprehensive score is greater than the preset comprehensive score threshold, determining that the comparison identification result is successful. Step S1043, when the comparison and identification results are all successful, confirming the route;
step S1044, performing an abnormal alarm when at least one of the comparison recognition results is a failure of the comparison recognition.
Further, fig. 7 shows an application architecture diagram of the system provided by the embodiment of the present invention.
In another preferred embodiment of the present invention, an unmanned aerial vehicle navigation system based on image recognition includes:
the navigation identifier selection unit 101 is configured to perform unmanned aerial vehicle navigation planning on a target unmanned aerial vehicle, obtain a navigation route of the unmanned aerial vehicle, analyze the navigation route of the unmanned aerial vehicle, and select a plurality of navigation passing identifiers.
In the embodiment of the present invention, the navigation identifier selection unit 101 obtains the flight destination position, determines a plurality of idle unmanned aerial vehicles in an idle state at this time, obtains the idle initial positions of the idle unmanned aerial vehicles, calculates the straight flight distance between the idle initial positions and the flight destination position, compares the flight distances, marks the idle initial position with the shortest flight distance as the target initial position, marks the idle unmanned aerial vehicle corresponding to the target initial position as the target unmanned aerial vehicle, performs the flight navigation planning of the unmanned aerial vehicle between the target initial position and the flight destination position, obtains the unmanned aerial vehicle navigation route, performs the identifier analysis on the unmanned aerial vehicle navigation route, and selects a plurality of navigation passing identifiers, wherein the plurality of navigation passing identifiers may be buildings, plants, roads, and the like.
Specifically, fig. 8 shows a block diagram of the navigation mark selecting unit 101 in the system according to the embodiment of the present invention.
In a preferred embodiment of the present invention, the navigation mark selecting unit 101 specifically includes:
A destination position acquisition module 1011 for acquiring a flight destination position;
An initial position obtaining module 1012, configured to select a target unmanned aerial vehicle according to the flight destination position, and obtain a target initial position;
the navigation planning module 1013 is configured to perform unmanned aerial vehicle navigation planning according to the target initial position and the flight destination position, and obtain an unmanned aerial vehicle navigation route;
The identifier selection module 1014 is configured to perform identifier analysis on the navigation route of the unmanned aerial vehicle, and select a plurality of navigation passing identifiers.
Further, the unmanned aerial vehicle navigation system based on image recognition further comprises:
The mark shooting planning unit 102 is configured to obtain a plurality of mark position data and a plurality of mark shape data of the navigation mark, and plan a plurality of mark shooting positions and a plurality of shooting gesture data according to a plurality of mark position data.
In the embodiment of the present invention, the identifier shooting planning unit 102 obtains a plurality of identifier shape data corresponding to a plurality of navigation passing identifiers based on a big data technology, obtains a plurality of identifier position data corresponding to a plurality of navigation passing identifiers, selects a plurality of identifier shooting positions from the unmanned aerial vehicle navigation route according to the plurality of identifier position data, and performs relative analysis on the plurality of identifier shooting positions and the plurality of identifier position data to plan a plurality of shooting gesture data, wherein the plurality of shooting gesture data all include shooting angles, shooting focal lengths, exposure, shutters, and the like.
Specifically, fig. 9 shows a block diagram of a structure of the identification shooting planning unit 102 in the system according to the embodiment of the present invention.
In a preferred embodiment of the present invention, the identification shooting planning unit 102 specifically includes:
A profile data acquisition module 1021, configured to acquire a plurality of identified profile data of the plurality of navigation identified;
a location data obtaining module 1022, configured to obtain a plurality of identified location data of the navigation identified;
A shooting position selection module 1023, configured to select a plurality of identification shooting positions from the unmanned aerial vehicle navigation route according to a plurality of the identification position data;
And a gesture data planning module 1024, configured to relatively analyze the plurality of identified shooting positions and the plurality of identified position data, and plan a plurality of shooting gesture data.
Further, the unmanned aerial vehicle navigation system based on image recognition further comprises:
The mark shooting control unit 103 is configured to, in the flight process of the unmanned aerial vehicle according to the navigation route of the unmanned aerial vehicle, shoot at a plurality of mark shooting positions according to a plurality of shooting gesture data, and obtain a plurality of mark shooting data.
In the embodiment of the invention, in the process of flying according to the navigation route of the unmanned aerial vehicle, the mark shooting control unit 103 positions the target unmanned aerial vehicle in real time to obtain real-time flying positions, generates a plurality of corresponding shooting control signals according to a plurality of shooting gesture data, further sends the corresponding shooting control signals to the target unmanned aerial vehicle when the real-time flying positions are one of the plurality of mark shooting positions, controls the target unmanned aerial vehicle to shoot the corresponding navigation passing mark, and feeds back mark shooting data, so that the plurality of mark shooting data can be obtained.
The image comparison and identification unit 104 is configured to compare and identify the plurality of pieces of identification shooting data according to the plurality of pieces of identification appearance data, and perform route confirmation or abnormality alarm according to the comparison and identification result.
In the embodiment of the present invention, the image comparison and identification unit 104 performs feature analysis on the plurality of identifier profile data, extracts a plurality of identifier profile features of an appearance, a color, and the like, performs comparison and identification on the plurality of identifier shooting data according to the plurality of identifier profile features, obtains a plurality of comparison and identification results, and performs route confirmation or abnormality alarm according to different comparison and identification results, and specifically: when the comparison and identification results are successful, confirming the route, and continuing normal flight; and when at least one comparison and identification result is that the comparison and identification is failed, carrying out abnormal alarm, and then carrying out flight adjustment.
Specifically, fig. 10 shows a block diagram of the image comparison and identification unit 104 in the system according to the embodiment of the present invention.
In a preferred embodiment of the present invention, the image comparison and identification unit 104 specifically includes:
a feature extraction module 1041, configured to extract a plurality of identification appearance features of the identification appearance data;
The comparison and identification module 1042 is used for comparing and identifying the plurality of the identification shooting data according to the plurality of the identification appearance characteristics to obtain a plurality of comparison and identification results;
The route confirmation module 1043 is configured to confirm the route when the comparison and recognition results are all the comparison and recognition results;
And the abnormality alarming module 1044 is configured to perform an abnormality alarm when at least one of the comparison recognition results is a comparison recognition failure.
It should be understood that, although the steps in the flowcharts of the embodiments of the present invention are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in various embodiments may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor do the order in which the sub-steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of the sub-steps or stages of other steps or other steps.
Those skilled in the art will appreciate that all or part of the processes in the methods of the above embodiments may be implemented by a computer program for instructing relevant hardware, where the program may be stored in a non-volatile computer readable storage medium, and where the program, when executed, may include processes in 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.
The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the invention and are described in detail herein without thereby limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (10)
1. The unmanned aerial vehicle navigation method based on image recognition is characterized by comprising the following steps of:
performing unmanned aerial vehicle navigation planning on a target unmanned aerial vehicle, acquiring an unmanned aerial vehicle navigation route, analyzing the unmanned aerial vehicle navigation route, and selecting a plurality of navigation passing identifiers;
acquiring a plurality of pieces of identification position data and a plurality of pieces of identification shape data of the navigation passing through the identification, and planning a plurality of pieces of identification shooting positions and a plurality of pieces of shooting gesture data according to the plurality of pieces of identification position data;
shooting the unmanned aerial vehicle according to a plurality of shooting gesture data at a plurality of mark shooting positions in the flying process of the unmanned aerial vehicle according to the unmanned aerial vehicle navigation route, and obtaining a plurality of mark shooting data;
according to the plurality of the identification appearance data, comparing and identifying the plurality of the identification shooting data, and carrying out route confirmation or abnormal alarm according to the comparison and identification result;
The unmanned aerial vehicle navigation planning is carried out on the target unmanned aerial vehicle, the unmanned aerial vehicle navigation route is obtained, the unmanned aerial vehicle navigation route is analyzed, and the selection of a plurality of navigation passing identifiers specifically comprises the following steps:
Acquiring a flight destination position;
selecting a target unmanned aerial vehicle according to the flight target position, and acquiring a target initial position;
According to the target initial position and the flight destination position, unmanned aerial vehicle navigation planning is carried out, and an unmanned aerial vehicle navigation route is obtained;
And carrying out identification analysis on the navigation route of the unmanned aerial vehicle, and selecting a plurality of navigation passing identifications.
2. The unmanned aerial vehicle navigation method based on image recognition according to claim 1, wherein the selecting a target unmanned aerial vehicle according to the flight destination position and acquiring the target initial position specifically comprises the following steps:
Determining a plurality of idle unmanned aerial vehicles;
Acquiring idle initial positions of a plurality of idle unmanned aerial vehicles;
Calculating flight distances between the idle initial positions and the flight destination positions;
comparing a plurality of flight distances, and marking the idle initial position with the shortest flight distance as a target initial position;
and selecting the target unmanned aerial vehicle according to the target initial position.
3. The unmanned aerial vehicle navigation method based on image recognition according to claim 2, wherein the method of calculating the flight distances of the plurality of idle initial positions from the flight destination position comprises the steps of:
Acquiring latitude and longitude corresponding to the idle initial position and latitude and longitude of the flight destination position;
according to the latitude and longitude corresponding to the idle initial position and the latitude and longitude of the flight destination position, respectively calculating to obtain a latitude difference value and a longitude difference value between the idle initial position and the flight destination position;
Calculating to obtain the flight distance between the idle initial position and the flight destination position according to the latitude difference value and the longitude difference value between the idle initial position and the flight destination position;
The calculation formula of the flight distance between the idle initial position and the flight destination position is expressed as follows:
；
wherein, Representing the flight distance of the idle initial position and the flight destination position,/>Representing the earth radius,/>Representing the difference in altitude between the idle initial position and the destination position,/>Representing the difference in longitude between the free initial position and the destination position,/>Latitude representing the free initial position,/>Latitude indicating the destination of the flight,/>Correction factor representing latitude term,/>A correction factor representing a longitude term.
4. A method of unmanned aerial vehicle navigation based on image recognition according to claim 3, wherein the method of unmanned aerial vehicle navigation planning and obtaining the unmanned aerial vehicle navigation route according to the target initial position and the flight destination position comprises the steps of:
Determining the target initial position and the flight destination position, and acquiring surrounding environment data, wherein the surrounding environment data comprises flight topography data, obstacle data and meteorological condition data;
calculating a preferred planning route between the target initial position and the flight destination position by using a routing algorithm based on the target initial position and the flight destination position in combination with the collected surrounding environment data;
The formula of the cost function corresponding to the routing algorithm is expressed as follows:
；
wherein, Representing the total cost of the cost function corresponding to the routing algorithm,/>Represents the/>Terrain threat cost of segment,/>Represents the/>Radar threat cost of segment,/>Represents the/>Flight distance cost of segment,/>Weight coefficient representing terrain threat item,/>Weight coefficient representing radar threat item,/>Weight coefficient representing flight distance item,/>Representing the number of segments into which the route is divided;
wherein the total cost function of the terrain threat is expressed as:
；
wherein, Representing the total cost of the terrain threat for the entire route;
The total cost function of flight distance is expressed as:
；
wherein, Total cost function representing flight distance,/>Representing a dot/>To the point/>Distance of/>Representing the total number of points on the route;
The total cost function of a radar threat is expressed as:
；
wherein, Representing the total cost function of a radar threat/>Representing the number of radar stations in the vicinity of the route,/>Represents the/>Performance factors of individual radar stations for representing the detection capabilities of the radar station,/>Representation of unmanned plane to the/>Distance of individual radar stations,/>Represents the/>Detecting capability correction factors corresponding to the radar stations;
And setting navigation parameters of the unmanned aerial vehicle according to the optimal planning route, and adjusting and optimizing the optimal planning route to obtain the unmanned aerial vehicle navigation route.
5. The unmanned aerial vehicle navigation method based on image recognition according to claim 4, wherein the steps of acquiring a plurality of the identified plurality of identified position data and a plurality of identified profile data, and planning a plurality of identified shooting positions and a plurality of shooting gesture data according to a plurality of the identified position data, specifically comprise the following steps:
acquiring a plurality of pieces of identification appearance data of a plurality of the navigation identifications;
Acquiring a plurality of pieces of identification position data of the navigation identified;
selecting a plurality of mark shooting positions from the unmanned aerial vehicle navigation route according to a plurality of mark position data;
and relatively analyzing the plurality of identification shooting positions and the plurality of identification position data, and planning a plurality of shooting gesture data.
6. The unmanned aerial vehicle navigation method based on image recognition according to claim 5, wherein the method of relatively analyzing the plurality of the identified shooting positions and the plurality of the identified position data and planning the plurality of shooting attitude data comprises the steps of:
determining the position of each mark and the corresponding mark shooting position, and analyzing and calculating the distance and angle between the position of each mark and the mark shooting position;
According to the distance and angle between the position of the mark and the shooting position of the mark, shooting gesture data corresponding to shooting equipment are calculated and determined, wherein the shooting gesture data comprise a rotation angle and a pitch angle;
wherein, the formula of calculation of the rotation angle that shooting equipment corresponds is expressed as:
；
wherein, Representing the corresponding rotation angle of the shooting equipment,/>Respectively represent the direction vector/>/>Component sum/>A component;
Direction vector Direction vector representing the position from the logo shooting position to the logo itself, direction vector/>The calculation formula of (2) is expressed as:
；
Wherein the coordinates of the position of the mark are Coordinates identifying the shooting position are/>The calculation formula of the pitch angle corresponding to the shooting equipment is expressed as follows:
；
wherein, Representing the pitch angle corresponding to the shooting equipment,/>Representing the direction vector/>The projection onto the horizontal plane is such that,。
7. The unmanned aerial vehicle navigation method based on image recognition according to claim 6, wherein in the unmanned aerial vehicle flying according to the unmanned aerial vehicle navigation route, shooting is performed at a plurality of mark shooting positions according to a plurality of shooting gesture data, and acquiring a plurality of mark shooting data specifically comprises the following steps:
Carrying out real-time positioning analysis on the unmanned aerial vehicle in the flying process according to the navigation route of the unmanned aerial vehicle;
generating a plurality of shooting control signals according to a plurality of shooting gesture data;
at a plurality of the identification shooting positions, respectively sending a plurality of shooting control signals to the target unmanned aerial vehicle;
and acquiring a plurality of identification shooting data transmitted by the feedback of the target unmanned aerial vehicle.
8. The unmanned aerial vehicle navigation method based on image recognition according to claim 7, wherein the comparing and recognizing the plurality of the identification shooting data according to the plurality of the identification appearance data, and performing route confirmation or abnormality warning according to the comparing and recognizing result specifically comprises the following steps:
Extracting identification appearance characteristics of a plurality of identification appearance data;
according to the appearance characteristics of the marks, comparing and identifying the shooting data of the marks to obtain a plurality of comparison and identification results;
when the comparison and identification results are successful, confirming the route;
when at least one comparison and identification result is that the comparison and identification fails, carrying out abnormal alarm;
the method for comparing and identifying the plurality of identification shooting data according to the appearance characteristics of the plurality of identifications and obtaining a plurality of comparison and identification results comprises the following steps:
Performing shape comparison recognition, color comparison recognition, texture comparison recognition and size proportion comparison recognition on the plurality of identification shooting data according to the plurality of identification appearance features to respectively obtain a shape recognition item score, a color recognition item score, a texture recognition item score and a size proportion recognition item score;
judging whether the shape recognition item score, the color recognition item score, the texture recognition item score and the size proportion recognition item score are all larger than a corresponding shape recognition item score threshold value, a color recognition item score threshold value, a texture recognition item score threshold value and a size proportion recognition item score threshold value;
if yes, calculating to obtain an identification comprehensive score for identifying shooting data based on the shape identification item score, the color identification item score, the texture identification item score and the size proportion identification item score;
Wherein, the calculation formula of the identification comprehensive score is expressed as follows:
；
wherein, Representing the recognition composite score,/>Representing shape recognition item score,/>Representing color recognition item score,/>Representing texture recognition term score,/>Representing size scale recognition term score,/>Weight factor representing shape recognition term,/>Weight factor representing color recognition term,/>Weight factor representing texture recognition term,/>A weight factor representing a size proportion identification term;
and when the identification comprehensive score is judged to be larger than a preset comprehensive score threshold value, determining that the comparison identification result is successful in comparison identification.
9. An unmanned aerial vehicle navigation system based on image recognition, wherein the system applies the unmanned aerial vehicle navigation method based on image recognition according to any one of the preceding claims 1 to 8, the system comprising a navigation identification selection unit, an identification shooting planning unit, an identification shooting control unit and an image comparison recognition unit, wherein:
The navigation mark selection unit is used for carrying out unmanned aerial vehicle navigation planning on a target unmanned aerial vehicle, acquiring an unmanned aerial vehicle navigation route, analyzing the unmanned aerial vehicle navigation route and selecting a plurality of navigation passing marks;
The mark shooting planning unit is used for acquiring a plurality of mark position data and a plurality of mark appearance data of the navigation mark, and planning a plurality of mark shooting positions and a plurality of shooting gesture data according to the plurality of mark position data;
The mark shooting control unit is used for shooting at a plurality of mark shooting positions according to a plurality of shooting gesture data in the flying process of the unmanned aerial vehicle according to the unmanned aerial vehicle navigation route, so as to obtain a plurality of mark shooting data;
And the image comparison and identification unit is used for comparing and identifying the plurality of the identification shooting data according to the plurality of the identification appearance data and carrying out route confirmation or abnormal alarm according to the comparison and identification result.
10. The unmanned aerial vehicle navigation system based on image recognition according to claim 9, wherein the navigation mark selection unit specifically comprises:
the target position acquisition module is used for acquiring a flight target position;
The initial position acquisition module is used for selecting a target unmanned aerial vehicle according to the flight target position and acquiring a target initial position;
The navigation planning module is used for carrying out unmanned aerial vehicle navigation planning according to the target initial position and the flight destination position, and obtaining an unmanned aerial vehicle navigation route;
The identification selection module is used for carrying out identification analysis on the navigation route of the unmanned aerial vehicle and selecting a plurality of navigation passing identifications;
the identification shooting planning unit specifically comprises:
The appearance data acquisition module is used for acquiring a plurality of pieces of identification appearance data of the navigation identified;
the position data acquisition module is used for acquiring a plurality of pieces of marked position data of the navigation marked;
The shooting position selection module is used for selecting a plurality of identification shooting positions from the unmanned aerial vehicle navigation route according to a plurality of identification position data;
The gesture data planning module is used for carrying out relative analysis on the plurality of identification shooting positions and the plurality of identification position data and planning a plurality of shooting gesture data;
the image comparison and identification unit specifically comprises:
The feature extraction module is used for extracting the identification appearance features of a plurality of identification appearance data;
the comparison and identification module is used for comparing and identifying the plurality of the identification shooting data according to the appearance characteristics of the plurality of the identifications and obtaining a plurality of comparison and identification results;
the route confirmation module is used for confirming the route when the comparison and identification results are successful;
And the abnormality alarm module is used for carrying out abnormality alarm when at least one comparison and identification result is that the comparison and identification fails.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410453274.XA CN118050007A (en) | 2024-04-16 | 2024-04-16 | Unmanned aerial vehicle navigation system and method based on image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410453274.XA CN118050007A (en) | 2024-04-16 | 2024-04-16 | Unmanned aerial vehicle navigation system and method based on image recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118050007A true CN118050007A (en) | 2024-05-17 |
Family
ID=91045257
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410453274.XA Pending CN118050007A (en) | 2024-04-16 | 2024-04-16 | Unmanned aerial vehicle navigation system and method based on image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118050007A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103822635A (en) * | 2014-03-05 | 2014-05-28 | 北京航空航天大学 | Visual information based real-time calculation method of spatial position of flying unmanned aircraft |
| CN109765930A (en) * | 2019-01-29 | 2019-05-17 | 理光软件研究所（北京）有限公司 | A kind of unmanned plane vision navigation system |
| CN109978425A (en) * | 2017-12-28 | 2019-07-05 | 航天信息股份有限公司 | A kind of unmanned plane express delivery delivery system, method and device |
| CN114492981A (en) * | 2022-01-24 | 2022-05-13 | 企知眼数据科技(浙江)有限公司 | Logistics distribution method and device based on cooperation of multiple unmanned aerial vehicles |
| CN116753917A (en) * | 2023-05-25 | 2023-09-15 | 云南电网有限责任公司电力科学研究院 | Positioning correction method, system, aircraft and computer readable storage device |
| CN117516531A (en) * | 2023-10-11 | 2024-02-06 | 广州市鑫广飞信息科技有限公司 | Unmanned plane control and navigation method, system, terminal and storage medium |
-
2024
- 2024-04-16 CN CN202410453274.XA patent/CN118050007A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103822635A (en) * | 2014-03-05 | 2014-05-28 | 北京航空航天大学 | Visual information based real-time calculation method of spatial position of flying unmanned aircraft |
| CN109978425A (en) * | 2017-12-28 | 2019-07-05 | 航天信息股份有限公司 | A kind of unmanned plane express delivery delivery system, method and device |
| CN109765930A (en) * | 2019-01-29 | 2019-05-17 | 理光软件研究所（北京）有限公司 | A kind of unmanned plane vision navigation system |
| CN114492981A (en) * | 2022-01-24 | 2022-05-13 | 企知眼数据科技(浙江)有限公司 | Logistics distribution method and device based on cooperation of multiple unmanned aerial vehicles |
| CN116753917A (en) * | 2023-05-25 | 2023-09-15 | 云南电网有限责任公司电力科学研究院 | Positioning correction method, system, aircraft and computer readable storage device |
| CN117516531A (en) * | 2023-10-11 | 2024-02-06 | 广州市鑫广飞信息科技有限公司 | Unmanned plane control and navigation method, system, terminal and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109324337B (en) | Unmanned aerial vehicle route generation and positioning method and device and unmanned aerial vehicle | |
| CN105466438B (en) | Sensor instrument distance in anticollision vehicle and application | |
| EP4318397A2 (en) | Method of computer vision based localisation and navigation and system for performing the same | |
| CN108109437B (en) | Unmanned aerial vehicle autonomous route extraction and generation method based on map features | |
| US9224050B2 (en) | Vehicle localization in open-pit mining using GPS and monocular camera | |
| US9188979B2 (en) | Method and system for remotely controlling a vehicle | |
| KR20210081984A (en) | Object change detection system for high definition map update and method thereof | |
| EP2818957A1 (en) | System and method for UAV landing | |
| US10739770B2 (en) | Autonomously-controlled inspection platform with model-based active adaptive data collection | |
| CN115917559A (en) | Trajectory prediction method, apparatus, computer device and storage medium | |
| US9816786B2 (en) | Method for automatically generating a three-dimensional reference model as terrain information for an imaging device | |
| EP3690400B1 (en) | Method and device for ego-vehicle localization to update hd map by using v2x information fusion | |
| CN112154429B (en) | High-precision map positioning method, system, platform and computer readable storage medium | |
| KR102289752B1 (en) | A drone for performring route flight in gps blocked area and methed therefor | |
| CN115861860A (en) | Target tracking and positioning method and system for unmanned aerial vehicle | |
| CN113239864A (en) | Route planning method of unmanned aerial vehicle suitable for agricultural investigation | |
| CN114689030A (en) | Unmanned aerial vehicle auxiliary positioning method and system based on airborne vision | |
| CN112689234B (en) | Indoor vehicle positioning method, device, computer equipment and storage medium | |
| CN111104861B (en) | Method and apparatus for determining wire position and storage medium | |
| CN118050007A (en) | Unmanned aerial vehicle navigation system and method based on image recognition | |
| CN118235171A (en) | Inspection of environmental sensing devices and/or environmental awareness of vehicles | |
| EP4068041A1 (en) | System and method for visual aided landing | |
| CN111860626B (en) | Water and soil conservation monitoring method and system based on unmanned aerial vehicle remote sensing and object-oriented classification | |
| CN116324338A (en) | Determining a starting position of a vehicle for positioning | |
| CN111414804B (en) | Identification frame determining method, identification frame determining device, computer equipment, vehicle and storage medium |
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 |