CN106950991A - A kind of unmanned plane based on image recognition makes a return voyage method - Google Patents
A kind of unmanned plane based on image recognition makes a return voyage method Download PDFInfo
- Publication number
- CN106950991A CN106950991A CN201710289539.7A CN201710289539A CN106950991A CN 106950991 A CN106950991 A CN 106950991A CN 201710289539 A CN201710289539 A CN 201710289539A CN 106950991 A CN106950991 A CN 106950991A
- Authority
- CN
- China
- Prior art keywords
- unmanned plane
- control system
- return voyage
- image recognition
- flight control
- 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
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
Abstract
Maked a return voyage method the invention discloses a kind of unmanned plane based on image recognition, it is related to unmanned plane field, including ground station control system, flight control system and unmanned plane body, the flight control system is arranged on unmanned plane body, magnetic compass is installed on the unmanned plane body, barometer and three axle high-definition tripod video cameras, the magnetic compass barometer and three axle high-definition tripod video cameras are connected with flight control system respectively, image processing module is provided with the flight control system, image storage module and picture recognition module, realization is maked a return voyage without gps signal unmanned plane.
Description
Technical field
The invention belongs to unmanned air vehicle technique field, specifically, the present invention relates to a kind of unmanned plane based on image recognition
Make a return voyage method.
Background technology
Traditional unmanned plane method of making a return voyage depends on the satellite positioning signals such as GPS, without gps signal or gps signal
Weak situation is entered, and unmanned plane, which can not be positioned, to make a return voyage.
The content of the invention
To achieve these goals, the technical scheme taken of the present invention is：A kind of unmanned plane based on image recognition makes a return voyage
Method, including ground station control system, flight control system and unmanned plane body, the flight control system are arranged on unmanned plane
On body, magnetic compass, barometer and three axle high-definition tripod video cameras, the magnetic compass air pressure are installed on the unmanned plane body
Meter and three axle high-definition tripod video cameras are connected with flight control system respectively, and image procossing is provided with the flight control system
Module, image storage module and picture recognition module.
It is preferred that, the shooting angle of the three axles high-definition tripod video camera is perpendicular to ground.
It is preferred that, preprogramming in information comparison module, described information comparing module is provided with the flight control system
Input has building, landform, directional information.
It is preferred that, algoritic module is provided with the flight control system.
The present invention provides a kind of unmanned plane based on image recognition and maked a return voyage method, high-definition tripod video camera during unmanned plane during flying
All the time locking direction angle, is obtained perpendicular to video informations such as building, the landform on ground in real time；Control system utilizes barometrical height
Degree and video camera shooting angle, are taken pictures according to algorithm, it is ensured that the photo-overlap area being continuously shot is not less than photo area
10%；Image processing module is superimposed the flying height information of magnetic compass information and unmanned plane in photo, makes in every photo
Containing direction and elevation information, and record and be continuously shot two image overlapping region information for k k+1k+2 ... .k+n, and by this
Information sequence is stored in image storage module；Picture recognition module by image processing algorithm extract image in building,
The information such as shape, direction, and set up course line characteristic information storehouse；Unmanned plane is obtained vertical in real time by high-definition tripod video camera when making a return voyage
The pictorial informations such as building, landform in ground, picture recognition module is to the building of extract real-time, landform, direction, flying height etc.
Information is matched with the feature stored in the characteristic information storehouse of course line；Compared by picture recognition module with information comparison module
To characteristic information, course back is fitted according to algorithm using overlapping image region, control unmanned plane during flying is to k+n, k+ (n-
1), above k+ (n-2) ... .., k regional center；Realize without making a return voyage under GPS states；Realization is maked a return voyage without gps signal unmanned plane.
Brief description of the drawings
A kind of unmanned plane based on image recognition that Fig. 1 is the present invention makes a return voyage the schematic block diagram of method；
Fig. 2 makes a return voyage the schematic diagram of method for a kind of unmanned plane based on image recognition of the present invention.
Embodiment
Below against accompanying drawing, by the description to embodiment, the embodiment to the present invention makees further details of
Explanation, it is therefore an objective to help those skilled in the art to the present invention design, technical scheme have more complete, accurate and deep reason
Solution, and contribute to it to implement.
As depicted in figs. 1 and 2, a kind of unmanned plane based on image recognition makes a return voyage method, including ground station control system, flies
Row control system and unmanned plane body, the flight control system are arranged on unmanned plane body, are pacified on the unmanned plane body
Equipped with magnetic compass, barometer and three axle high-definition tripod video cameras, the magnetic compass barometer and three axle high-definition tripod video cameras
It is connected respectively with flight control system, image processing module, image storage module and image is provided with the flight control system
Identification module.
In the present embodiment, the shooting angle of the three axles high-definition tripod video camera is perpendicular to ground.
In the present embodiment, it is provided with pre- in information comparison module, described information comparing module in the flight control system
First programming input has building, landform, directional information.
In the present embodiment, algoritic module is provided with the flight control system.
The present invention provides a kind of unmanned plane based on image recognition and maked a return voyage method, high-definition tripod video camera during unmanned plane during flying
All the time locking direction angle, is obtained perpendicular to video informations such as building, the landform on ground in real time；Control system utilizes barometrical height
Degree and video camera shooting angle, are taken pictures according to algorithm, it is ensured that the photo-overlap area being continuously shot is not less than photo area
10%；Image processing module is superimposed the flying height information of magnetic compass information and unmanned plane in photo, makes in every photo
Containing direction and elevation information, and record and be continuously shot two image overlapping region information for k k+1k+2 ... .k+n, and by this
Information sequence is stored in image storage module；Picture recognition module by image processing algorithm extract image in building,
The information such as shape, direction, and set up course line characteristic information storehouse；Unmanned plane is obtained vertical in real time by high-definition tripod video camera when making a return voyage
The pictorial informations such as building, landform in ground, picture recognition module is to the building of extract real-time, landform, direction, flying height etc.
Information is matched with the feature stored in the characteristic information storehouse of course line；Compared by picture recognition module with information comparison module
To characteristic information, course back is fitted according to algorithm using overlapping image region, control unmanned plane during flying is to k+n, k+ (n-
1), above k+ (n-2) ... .., k regional center；Realize without making a return voyage under GPS states；Realization is maked a return voyage without gps signal unmanned plane.
The present invention is exemplarily described above in association with accompanying drawing, it is clear that the present invention is implemented not by above-mentioned side
The limitation of formula, as long as employ the improvement for the various unsubstantialities that method of the present invention design and technical scheme are carried out；Or not
It is improved, the above-mentioned design of the present invention and technical scheme are directly applied into other occasions, in protection scope of the present invention
Within.
Claims (4)
- A kind of method 1. unmanned plane based on image recognition makes a return voyage, it is characterised in that：Including ground station control system, flight control System and unmanned plane body, the flight control system are arranged on unmanned plane body, and magnetic is provided with the unmanned plane body Compass, barometer and three axle high-definition tripod video cameras, the magnetic compass barometer and three axle high-definition tripod video cameras respectively with Flight control system is connected, and image processing module, image storage module and image recognition mould are provided with the flight control system Block.
- The method 2. a kind of unmanned plane based on image recognition according to claim 1 makes a return voyage, it is characterised in that：Three axle The shooting angle of high-definition tripod video camera is perpendicular to ground.
- The method 3. a kind of unmanned plane based on image recognition according to claim 1 makes a return voyage, it is characterised in that：The flight Preprogramming input in information comparison module, described information comparing module is provided with control system building, landform, direction letter Breath.
- The method 4. a kind of unmanned plane based on image recognition according to claim 1 makes a return voyage, it is characterised in that：The flight Algoritic module is provided with control system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710289539.7A CN106950991A (en) | 2017-04-27 | 2017-04-27 | A kind of unmanned plane based on image recognition makes a return voyage method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710289539.7A CN106950991A (en) | 2017-04-27 | 2017-04-27 | A kind of unmanned plane based on image recognition makes a return voyage method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106950991A true CN106950991A (en) | 2017-07-14 |
Family
ID=59477585
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710289539.7A Pending CN106950991A (en) | 2017-04-27 | 2017-04-27 | A kind of unmanned plane based on image recognition makes a return voyage method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106950991A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109561282A (en) * | 2018-11-22 | 2019-04-02 | 亮风台（上海）信息科技有限公司 | A kind of method and apparatus of the action of ground for rendering auxiliary information |
| WO2021237481A1 (en) * | 2020-05-26 | 2021-12-02 | 深圳市大疆创新科技有限公司 | Control method and device for unmanned aerial vehicle |
| CN114742793A (en) * | 2022-04-06 | 2022-07-12 | 广东水电二局股份有限公司 | Monitoring and correcting method based on engineering surveying and mapping |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101157484B1 (en) * | 2010-12-14 | 2012-06-20 | 주식회사 대한항공 | Uav automatic recovering method |
| CN104807456A (en) * | 2015-04-29 | 2015-07-29 | 深圳市保千里电子有限公司 | Method for automatic return flight without GPS (global positioning system) signal |
| CN105335733A (en) * | 2015-11-23 | 2016-02-17 | 西安韦德沃德航空科技有限公司 | Autonomous landing visual positioning method and system for unmanned aerial vehicle |
| CN106054931A (en) * | 2016-07-29 | 2016-10-26 | 北方工业大学 | Unmanned aerial vehicle fixed-point flight control system based on visual positioning |
| CN106325299A (en) * | 2016-09-13 | 2017-01-11 | 上海顺砾智能科技有限公司 | Unmanned plane return flight landing method based on visual sense |
| CN106325305A (en) * | 2015-06-29 | 2017-01-11 | 优利科技有限公司 | Geo-location or navigation type camera, aircraft, and navigation method and system thereof |
-
2017
- 2017-04-27 CN CN201710289539.7A patent/CN106950991A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101157484B1 (en) * | 2010-12-14 | 2012-06-20 | 주식회사 대한항공 | Uav automatic recovering method |
| CN104807456A (en) * | 2015-04-29 | 2015-07-29 | 深圳市保千里电子有限公司 | Method for automatic return flight without GPS (global positioning system) signal |
| CN106325305A (en) * | 2015-06-29 | 2017-01-11 | 优利科技有限公司 | Geo-location or navigation type camera, aircraft, and navigation method and system thereof |
| CN105335733A (en) * | 2015-11-23 | 2016-02-17 | 西安韦德沃德航空科技有限公司 | Autonomous landing visual positioning method and system for unmanned aerial vehicle |
| CN106054931A (en) * | 2016-07-29 | 2016-10-26 | 北方工业大学 | Unmanned aerial vehicle fixed-point flight control system based on visual positioning |
| CN106325299A (en) * | 2016-09-13 | 2017-01-11 | 上海顺砾智能科技有限公司 | Unmanned plane return flight landing method based on visual sense |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109561282A (en) * | 2018-11-22 | 2019-04-02 | 亮风台（上海）信息科技有限公司 | A kind of method and apparatus of the action of ground for rendering auxiliary information |
| WO2021237481A1 (en) * | 2020-05-26 | 2021-12-02 | 深圳市大疆创新科技有限公司 | Control method and device for unmanned aerial vehicle |
| CN114742793A (en) * | 2022-04-06 | 2022-07-12 | 广东水电二局股份有限公司 | Monitoring and correcting method based on engineering surveying and mapping |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103347785B (en) | A kind of unmanned plane automatic recovery method | |
| KR102018892B1 (en) | Method and apparatus for controlling take-off and landing of unmanned aerial vehicle | |
| Yol et al. | Vision-based absolute localization for unmanned aerial vehicles | |
| Viswanathan et al. | Vision based robot localization by ground to satellite matching in gps-denied situations | |
| CN102353377B (en) | High altitude long endurance unmanned aerial vehicle integrated navigation system and navigating and positioning method thereof | |
| CN106950991A (en) | A kind of unmanned plane based on image recognition makes a return voyage method | |
| CN107727079A (en) | The object localization method of camera is regarded under a kind of full strapdown of Small and micro-satellite | |
| WO2016141100A3 (en) | Scanning environments and tracking unmanned aerial vehicles | |
| KR101898782B1 (en) | Apparatus for tracking object | |
| CN106197422A (en) | A kind of unmanned plane based on two-dimensional tag location and method for tracking target | |
| CN104807456B (en) | A kind of method maked a return voyage automatically during GPS no signals | |
| CN105501457A (en) | Infrared vision based automatic landing guidance method and system applied to fixed-wing UAV (unmanned aerial vehicle) | |
| CN110186468B (en) | High-precision map making method and device for automatic driving | |
| CN104006708A (en) | Scene matching based ground target indirect locating method | |
| CN106325299A (en) | Unmanned plane return flight landing method based on visual sense | |
| CN108955685A (en) | A kind of tanker aircraft tapered sleeve pose measuring method based on stereoscopic vision | |
| CN111045455A (en) | Visual correction method for flight course angle error of indoor corridor of micro unmanned aerial vehicle | |
| CN204956941U (en) | A airborne system for unmanned aerial vehicle helps and falls vision -guided | |
| US20150367957A1 (en) | Providing visibility to a vehicle's environment via a set of cameras which is conformal to the vehicle | |
| CN114184200A (en) | Multi-source fusion navigation method combined with dynamic mapping | |
| US20130141540A1 (en) | Target locating method and a target locating system | |
| Gao et al. | Automatic extraction of multi-vehicle trajectory based on traffic videotaping from quadcopter model | |
| CN114689030A (en) | Unmanned aerial vehicle auxiliary positioning method and system based on airborne vision | |
| KR20190012439A (en) | Apparatus and method for correcting position of drone | |
| CN111881878B (en) | Lane line identification method for look-around multiplexing |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170714 |