CN109460046A - A kind of unmanned plane identify naturally not with independent landing method - Google Patents
A kind of unmanned plane identify naturally not with independent landing method Download PDFInfo
- Publication number
- CN109460046A CN109460046A CN201811213147.3A CN201811213147A CN109460046A CN 109460046 A CN109460046 A CN 109460046A CN 201811213147 A CN201811213147 A CN 201811213147A CN 109460046 A CN109460046 A CN 109460046A
- Authority
- CN
- China
- Prior art keywords
- unmanned plane
- point
- coordinate
- image
- region
- 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.)
- Granted
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
- G05D1/04—Control of altitude or depth
- G05D1/06—Rate of change of altitude or depth
- G05D1/0607—Rate of change of altitude or depth specially adapted for aircraft
- G05D1/0653—Rate of change of altitude or depth specially adapted for aircraft during a phase of take-off or landing
- G05D1/0676—Rate of change of altitude or depth specially adapted for aircraft during a phase of take-off or landing specially adapted for landing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/48—Extraction of image or video features by mapping characteristic values of the pattern into a parameter space, e.g. Hough transformation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/757—Matching configurations of points or features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Remote Sensing (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Astronomy & Astrophysics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Automation & Control Theory (AREA)
- Image Analysis (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
A kind of unmanned plane identify naturally not with independent landing method category machine vision navigation technical field, the present invention determines touchdown area according to given pre- landing coordinate on satellite digital map, Aerial Images are shot in pre- landing coordinate using unmanned plane, satellite digital map is filtered with Aerial Images, gray processing, binary conversion treatment, Edge Gradient Feature and Hough transform, extract continuous geometry curve, and the two is matched using Weighted Hausdorff distance matching algorithm, coordinate of the centroid in region in unmanned plane image relative to unmanned plane is calculated according to Green's theorem, according to the space coordinate of projection relation zoning centroid, and guide unmanned plane in the space coordinate independent landing of regional centroid.The present invention can guarantee the unmanned plane best landing point of autonomous classification within the specified range, and precisely land, and can make up the deficiency that independent landing error is big under GPS navigation, and the safety and reliability of independent landing is improved.
Description
Technical field
The invention belongs to machine vision navigation technical fields, and in particular to a kind of unmanned plane does not identify not and independent landing naturally
Method.
Background technique
In recent years, with the development of micro- inertial navigation system, flight control system, MEMS and new material, miniature drone
Research achieve great progress.Wherein rotary wind type Small and micro-satellite is good, compact-sized, at low cost with flexibility, obtains
Access according to it is quick the features such as, application range also covers various fields, including but not limited to pesticide spraying, geological exploration, search
With rescue, cargo transport and mapping etc..The reaction speed of information and the limitation of working efficiency are obtained due to people, these
Business is independently completed by unmanned plane as far as possible, realizes autonomous landing, path by the contexture by self of blas or unmanned plane
Planning, avoidance and imitative fly etc. act, and guarantee the accuracy and reliability of operation process.
In terms of unmanned plane independent landing, using more at present is the independent landing mode based on GPS navigation, i.e., by nothing
Geographical coordinate locating for man-machine included GPS sensor record takeoff opportunity body, or by artificially specifying some geographical coordinate, in nothing
When man-machine landing, is hovered by GPS positioning system guidance unmanned plane in the geographical coordinate overhead recorded and decline landing.And GPS
Navigation causes unmanned plane to be located in remote or shelter more there is big, the disadvantages such as positioning accuracy is low are interfered by non-air medium
Regional independent landing error it is big, can not accurately complete landing task.
Unmanned plane independent landing method based on machine vision is to solve one of the approach of GPS system position inaccurate, mesh
Preceding apply more on rotor wing unmanned aerial vehicle is the independent landing method based on artificial landmark.And as unmanned plane is in every field
Using more and more extensive, the adaptive capacity to environment of unmanned plane is required also higher and higher.Some specific mission requirements nobody
Machine lands in the place that should not place artificial landmark, or even unmanned plane is required independently to find suitable land in specific region
Place, this requires unmanned planes to possess identification target ability naturally.Therefore, believe to provide accurately navigation to unmanned plane
Breath, completes specific independent landing task, need the mark naturally of unmanned plane a kind of not with independent landing method.
Summary of the invention
It is an object of the invention to above-mentioned prior art there are aiming at the problem that, propose a kind of based on machine vision and satellite
The unmanned plane of numerical map identifies naturally not to be sat using satellite digital map in given pre- landing with independent landing method
Mark nearby finds suitable touchdown area, and the Aerial Images of unmanned plane single camera vision system and satellite digital map is made to carry out image
Matching, by the processing to unmanned plane image, is calculated best with eliminating the error of GPS navigation in touchdown area
Land point coordinate, is precisely landed.
Unmanned plane of the invention identifies naturally not to be included the following steps: with independent landing method
1.1 according to given pre- landing coordinate (X0,Y0,Z0), determine that one piece of profile is convex polygon on satellite digital map
The touchdown area P of shape is first filtered the image of region P, gray processing and binary conversion treatment, further implements edge feature
It extracts, rejects the miscellaneous point in part, retain the main edge feature based on region, extract continuous geometry curve finally by Hough transform,
Obtain the contour curve I and reference picture A of region P on satellite digital map, wherein binary conversion treatment uses maximum between-cluster variance
Method；
Aerial Images are filtered, gray processing and binaryzation to given pre- landing coordinate overhead by 1.2 unmanned plane during flyings
Edge Gradient Feature is further implemented in processing, rejects the miscellaneous point in part, retains the main edge feature based on region, finally by
Hough transform extracts continuous geometry curve, obtains the contour curve II and measuring image B of region P on satellite digital map,
In, binary conversion treatment equally uses maximum variance between clusters；
1.3 match the reference picture A that step 1.1 obtains with the measuring image B that step 1.2 obtains, in unmanned plane
Touchdown area P is confirmed in Aerial Images；Images match uses Weighted Hausdorff distance matching algorithm, including the following steps:
1.3.1 in reference picture A and measuring image B, feature point set is carried out in two-dimensional space using 3-4DT algorithm
Distance conversion, obtains image distance transition matrix JAAnd JB；
1.3.2 the branch point in reference picture A and measuring image B is extracted, and is respectively stored into matrix A and B；
1.3.3 according to JA、JB, A and B calculate Weighted Hausdorff distance:
H (A, B)=max (hWHD(A,B),hWHD(B,A))
Wherein: A, B is two point sets；NaIt is the sum of characteristic point in point set A；A is a characteristic point for belonging to A；d(a,
B) be on point set A characteristic point a to the distance of point set B；hWHD(A, B) is represented from point set A to the directed distance of point set B；hWHD(B,A)
It represents from point set B to the directed distance of point set A；
Point with minimum Hausdorff distance is exactly final match point, thus obtains preliminary location information；
1.3.4 all matching double points are corresponded using least-squares algorithm, to obtain more accurate position
Confidence breath；
1.4 establish two-dimensional surface rectangular coordinate system by coordinate origin of unmanned plane camera, calculate nothing according to Green's theorem
Coordinate (x of the centroid of region P relative to unmanned plane in man-machine Aerial Imagesc,yc)；
1.5 according to the coordinate (X of the projection relation zoning p-shaped heartc,Yc,Zc), it specifically includes:
1.5.1 ground resolution GSD is calculated:
Wherein: GSD indicates ground resolution (m)；F is lens focus (mm)；P is the pixel dimension of imaging sensor
(mm)；H is the corresponding flying height (m) of unmanned plane；
1.5.2 it calculates image diagonal line True Ground Range and image diagonal is obtained according to the width w and height h of image
Ground distance L between line:
Wherein: GSD indicates ground resolution (m)；W is image width；H is image height；
1.5.3 region is acquired with respect to the distance and deflection of central point according to image center point longitude and latitude and the region p-shaped heart
The geographical coordinate of the p-shaped heart:
Wherein: θ0∈(0,2π)；LonaFor the longitude of image center point；LataFor the latitude of image center point；RiFor equator
Radius takes 6378137m；RjFor polar radius, 6356725m is taken；
1.5.4 geographical coordinate is carried out to the conversion of space coordinate, obtains the space coordinate (X of the region p-shaped heartc,Yc,Zc):
Wherein: N is radius of curvature；Lon is longitude；Lat is latitude；H is elevation；
1.6 unmanned plane during flyings are to space coordinate (Xc,Yc,Zc) overhead, carry out vertical direction landing.
The present invention can guarantee the unmanned plane best landing point of autonomous classification within the specified range, and precisely land, and can make up GPS
The big deficiency of lower independent landing error of navigating, and the safety and reliability of independent landing is improved.
Detailed description of the invention
Fig. 1 is that unmanned plane identifies the flow chart not with independent landing method naturally
Specific embodiment
For the purposes, technical schemes and advantages in the present invention are more clearly understood, following present invention is further specifically
It is bright.
Step 1, according to given pre- landing coordinate (X0,Y0,Z0), determined on satellite digital map one piece it is suitable
Land region P (it is required that the region contour is convex polygon), is first filtered the image of region P, gray processing processing, two-value
Change processing, further implements Edge Gradient Feature, rejects the miscellaneous point in part, retains the main edge feature based on region, finally leads to
It crosses Hough transform extraction continuous geometry curve and obtains the contour curve of region P on satellite digital map, obtain reference picture A,
In, binary conversion treatment selects maximum variance between clusters, it is assumed that T is the global threshold chosen, by the pixel of image all pixels point
It is that line of demarcation is divided into foreground and background, ω according to T1And ω2It respectively indicates to belong to background and belong to foreground pixel and accounts for entire image
Ratio, then:
Wherein: p (i) indicates that pixel value is the probability that the pixel of i occurs in the picture.
μ0And μ1The average value of background and foreground pixel point pixel is respectively indicated, μ is the average pixel value of all pixels point,
Then:
The corresponding inter-class variance σ of the threshold value2(T) is defined as:
σ2(T)=ω0(T)[μ0(T)-μ(T)]2+ω1(T)[μ1(T)-μ(T)]2=ω0(T)ω1(T)[μ0(T)-μ1(T)]2
Each gray value is traversed, the maximum corresponding threshold value T of inter-class variance, as required threshold value are found.
Near unmanned plane during flying to given pre- landing coordinate overhead, Aerial Images are filtered for step 2, ash
Degreeization processing, binary conversion treatment further implement Edge Gradient Feature, reject the miscellaneous point in part, retain the main side based on region
Edge feature extracts continuous geometry curve finally by Hough transform and obtains the contour curve of region P on satellite digital map, obtains
To measuring image B.Wherein, binary conversion treatment equally selects maximum variance between clusters.
Reference picture A is matched with measuring image B, confirms touchdown area in unmanned plane image by step 3
P.Images match uses Weighted Hausdorff distance matching algorithm, the specific steps are as follows:
(1) in reference picture A and measuring image B, using 3-4DT algorithm carry out feature point set in two-dimensional space away from
From conversion, image distance transition matrix J is obtainedAAnd JB；
(2) branch point in reference picture A and measuring image B is extracted, and is respectively stored into matrix A and B；
(3) according to JA、JB, A and B calculate Weighted Hausdorff distance:
H (A, B)=max (hWHD(A,B),hWHD(B,A))
Wherein: A, B is two point sets, NaIt is the sum of characteristic point in point set A, a is a characteristic point for belonging to A, d (a,
It B) is distance of the characteristic point a to point set B, h on point set AWHD(A,B)、hWHD(B, A) respectively represented from point set A to point set B and from
Directed distance of the point set B to point set A.
Point with minimum Hausdorff distance is exactly thus final match point obtains preliminary location information.
(4) all matching double points are corresponded using least-squares algorithm, to obtain more accurate position
Information.
Step 4 establishes two-dimensional surface rectangular coordinate system by coordinate origin of unmanned plane camera, calculates unmanned plane
Coordinate (x of the centroid of region P relative to unmanned plane in imagec,yc)。
According to Green's theorem, the closed contour along region P is integrated:
After discretization, above formula conversion are as follows:
Step 5, according to the coordinate (X of the projection relation zoning p-shaped heartc,Yc,Zc):
(1) ground resolution is calculated:
Wherein: GSD indicates ground resolution (m), and f is lens focus (mm), and P is the pixel dimension of imaging sensor
(mm), H is the corresponding flying height (m) of unmanned plane.
(2) image diagonal line True Ground Range is calculated, image diagonal line is obtained according to the width w of image and height h
Between ground distance:
(3) region P is acquired with respect to the distance and deflection of central point according to image center point longitude and latitude and the region p-shaped heart
The geographical coordinate of centroid:
Wherein: θ0∈(0,2π),Lona、LataFor the longitude and latitude of image center point, Ri6378137m, R are taken for equatorial radiusj
6356725m is taken for polar radius.
(4) it carries out geographical coordinate and is transformed between space the conversion between coordinate system
Wherein: N is radius of curvature, and Lon, Lat, H are respectively longitude, latitude and elevation, and the space for obtaining the region p-shaped heart is sat
Mark (Xc,Yc,Zc)。
Step 6, unmanned plane during flying to space coordinate (Xc,Yc,Zc) overhead, carry out vertical direction landing.
Claims (1)
1. a kind of unmanned plane identify naturally not with independent landing method, it is characterised in that include the following steps:
1.1 according to given pre- landing X0,Y0,Z0Coordinate, on satellite digital map determine one piece of profile be convex polygon
Land region P is first filtered the image of region P, gray processing and binary conversion treatment, further implements Edge Gradient Feature,
The miscellaneous point in part is rejected, the main edge feature based on region is retained, continuous geometry curve is extracted finally by Hough transform, obtains
The contour curve I and reference picture A of region P on satellite digital map, wherein binary conversion treatment uses maximum variance between clusters；
Aerial Images are filtered, at gray processing and binaryzation by 1.2 unmanned plane during flyings to given pre- landing coordinate overhead
Reason further implements Edge Gradient Feature, rejects the miscellaneous point in part, retains the main edge feature based on region, finally by
Hough transform extracts continuous geometry curve, obtains the contour curve II and measuring image B of region P on satellite digital map,
In, binary conversion treatment equally uses maximum variance between clusters；
1.3 match the reference picture A that step 1.1 obtains with the measuring image B that step 1.2 obtains, in unmanned plane
Touchdown area P is confirmed in image；Images match uses Weighted Hausdorff distance matching algorithm, including the following steps:
1.3.1 in reference picture A and measuring image B, distance of the feature point set in two-dimensional space is carried out using 3-4DT algorithm
Conversion, obtains image distance transition matrix JAAnd JB；
1.3.2 the branch point in reference picture A and measuring image B is extracted, and is respectively stored into matrix A and B；
1.3.3 according to JA、JB, A and B calculate Weighted Hausdorff distance:
H (A, B)=max (hWHD(A,B),hWHD(B,A))
Wherein: A, B is two point sets；NaFor the sum of characteristic point in point set A；A is a characteristic point for belonging to A；D (a, B) is a little
Collect the distance of characteristic point a to point set B on A；hWHD(A, B) is represented from point set A to the directed distance of point set B；hWHD(B, A) represent from
Directed distance of the point set B to point set A；
Point with minimum Hausdorff distance is exactly final match point, thus obtains preliminary location information；
1.3.4 all matching double points are corresponded using least-squares algorithm, to obtain more accurate position letter
Breath；
1.4 establish two-dimensional surface rectangular coordinate system by coordinate origin of unmanned plane camera, calculate unmanned plane according to Green's theorem
X of the centroid of region P relative to unmanned plane in Aerial Imagesc,ycCoordinate；
1.5 according to the X of the projection relation zoning p-shaped heartc,Yc,ZcCoordinate specifically includes:
1.5.1 ground resolution GSD is calculated:
Wherein: GSD indicates ground resolution (m)；F is lens focus (mm)；P is the pixel dimension (mm) of imaging sensor；H is
The corresponding flying height (m) of unmanned plane；
1.5.2 calculate image diagonal line True Ground Range, according to the width w and height h of image, obtain image diagonal line it
Between ground distance L:
Wherein: GSD indicates ground resolution (m)；W is image width；H is image height；
1.5.3 region p-shaped is acquired with respect to the distance and deflection of central point according to image center point longitude and latitude and the region p-shaped heart
The geographical coordinate of the heart:
Wherein: θ0∈(0,2π)；LonaFor the longitude of image center point；LataFor the latitude of image center point；RiFor equatorial radius,
Take 6378137m；RjFor polar radius, 6356725m is taken；
1.5.4 geographical coordinate is carried out to the conversion of space coordinate, obtains the space coordinate X of the region p-shaped heartc,Yc,Zc:
Wherein: N is radius of curvature；Lon is longitude；Lat is latitude；H is elevation；
1.6 unmanned plane during flyings are to space coordinate Xc,Yc,ZcOverhead carries out vertical direction landing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811213147.3A CN109460046B (en) | 2018-10-17 | 2018-10-17 | Unmanned aerial vehicle natural landmark identification and autonomous landing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811213147.3A CN109460046B (en) | 2018-10-17 | 2018-10-17 | Unmanned aerial vehicle natural landmark identification and autonomous landing method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109460046A true CN109460046A (en) | 2019-03-12 |
| CN109460046B CN109460046B (en) | 2021-08-06 |
Family
ID=65607782
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811213147.3A Active CN109460046B (en) | 2018-10-17 | 2018-10-17 | Unmanned aerial vehicle natural landmark identification and autonomous landing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109460046B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110968112A (en) * | 2019-12-12 | 2020-04-07 | 哈尔滨工程大学 | Unmanned aerial vehicle autonomous landing system and method based on monocular vision |
| CN111324145A (en) * | 2020-02-28 | 2020-06-23 | 厦门理工学院 | Unmanned aerial vehicle autonomous landing method, device, equipment and storage medium |
| CN111626260A (en) * | 2020-06-05 | 2020-09-04 | 贵州省草业研究所 | Aerial photo ground object feature point extraction method based on unmanned aerial vehicle remote sensing technology |
| CN112419374A (en) * | 2020-11-11 | 2021-02-26 | 北京航空航天大学 | Unmanned aerial vehicle positioning method based on image registration |
| CN114998773A (en) * | 2022-08-08 | 2022-09-02 | 四川腾盾科技有限公司 | Characteristic mismatching elimination method and system suitable for aerial image of unmanned aerial vehicle system |
| CN115526896A (en) * | 2021-07-19 | 2022-12-27 | 中核利华消防工程有限公司 | Fire prevention and control method and device, electronic equipment and readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20100095665A (en) * | 2009-02-12 | 2010-09-01 | 한양대학교 산학협력단 | Automatic landing method, landing apparatus of scanning probe microscope and scanning probe microscope using the same |
| CN103424126A (en) * | 2013-08-12 | 2013-12-04 | 西安电子科技大学 | System and method for verifying visual autonomous landing simulation of unmanned aerial vehicle |
| CN105000194A (en) * | 2015-08-13 | 2015-10-28 | 史彩成 | UAV (unmanned aerial vehicle) assisted landing visual guiding method and airborne system based on ground cooperative mark |
| CN105550994A (en) * | 2016-01-26 | 2016-05-04 | 河海大学 | Satellite image based unmanned aerial vehicle image rapid and approximate splicing method |
| CN107063261A (en) * | 2017-03-29 | 2017-08-18 | 东北大学 | The multicharacteristic information terrestrial reference detection method precisely landed for unmanned plane |
-
2018
- 2018-10-17 CN CN201811213147.3A patent/CN109460046B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20100095665A (en) * | 2009-02-12 | 2010-09-01 | 한양대학교 산학협력단 | Automatic landing method, landing apparatus of scanning probe microscope and scanning probe microscope using the same |
| CN103424126A (en) * | 2013-08-12 | 2013-12-04 | 西安电子科技大学 | System and method for verifying visual autonomous landing simulation of unmanned aerial vehicle |
| CN105000194A (en) * | 2015-08-13 | 2015-10-28 | 史彩成 | UAV (unmanned aerial vehicle) assisted landing visual guiding method and airborne system based on ground cooperative mark |
| CN105550994A (en) * | 2016-01-26 | 2016-05-04 | 河海大学 | Satellite image based unmanned aerial vehicle image rapid and approximate splicing method |
| CN107063261A (en) * | 2017-03-29 | 2017-08-18 | 东北大学 | The multicharacteristic information terrestrial reference detection method precisely landed for unmanned plane |
Non-Patent Citations (2)
| Title |
|---|
| 李宇 等: "基于视觉的无人机自主着陆地标识别方法", 《计算机应用研究》 * |
| 陈勇 等: "新型的无人机自主着陆地标设计与研究", 《电子科技大学学报》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110968112A (en) * | 2019-12-12 | 2020-04-07 | 哈尔滨工程大学 | Unmanned aerial vehicle autonomous landing system and method based on monocular vision |
| CN111324145A (en) * | 2020-02-28 | 2020-06-23 | 厦门理工学院 | Unmanned aerial vehicle autonomous landing method, device, equipment and storage medium |
| CN111324145B (en) * | 2020-02-28 | 2022-08-16 | 厦门理工学院 | Unmanned aerial vehicle autonomous landing method, device, equipment and storage medium |
| CN111626260A (en) * | 2020-06-05 | 2020-09-04 | 贵州省草业研究所 | Aerial photo ground object feature point extraction method based on unmanned aerial vehicle remote sensing technology |
| CN112419374A (en) * | 2020-11-11 | 2021-02-26 | 北京航空航天大学 | Unmanned aerial vehicle positioning method based on image registration |
| CN112419374B (en) * | 2020-11-11 | 2022-12-27 | 北京航空航天大学 | Unmanned aerial vehicle positioning method based on image registration |
| CN115526896A (en) * | 2021-07-19 | 2022-12-27 | 中核利华消防工程有限公司 | Fire prevention and control method and device, electronic equipment and readable storage medium |
| CN114998773A (en) * | 2022-08-08 | 2022-09-02 | 四川腾盾科技有限公司 | Characteristic mismatching elimination method and system suitable for aerial image of unmanned aerial vehicle system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109460046B (en) | 2021-08-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109460046A (en) | A kind of unmanned plane identify naturally not with independent landing method | |
| CN106054929B (en) | A kind of unmanned plane based on light stream lands bootstrap technique automatically | |
| CN109992006B (en) | A kind of accurate recovery method and system of power patrol unmanned machine | |
| CN106647814B (en) | A kind of unmanned plane vision auxiliary positioning and flight control system and method based on the identification of two dimensional code terrestrial reference | |
| US10778967B2 (en) | Systems and methods for improving performance of a robotic vehicle by managing on-board camera defects | |
| CN107544550B (en) | Unmanned aerial vehicle automatic landing method based on visual guidance | |
| Martínez et al. | On-board and ground visual pose estimation techniques for UAV control | |
| CN103822635B (en) | The unmanned plane during flying spatial location real-time computing technique of view-based access control model information | |
| CN103411609B (en) | A kind of aircraft return route planing method based on online composition | |
| WO2018035835A1 (en) | Methods and system for autonomous landing | |
| CN105644785B (en) | A kind of UAV Landing method detected based on optical flow method and horizon | |
| CN110569838A (en) | Autonomous landing method of quad-rotor unmanned aerial vehicle based on visual positioning | |
| CN111492326A (en) | Image-based positioning for unmanned aerial vehicles and related systems and methods | |
| CN110221625A (en) | The Autonomous landing guidance method of unmanned plane exact position | |
| CN110222612A (en) | Dynamic target recognition and tracking for unmanned plane Autonomous landing | |
| CN111024072B (en) | Satellite map aided navigation positioning method based on deep learning | |
| CN109341686B (en) | Aircraft landing pose estimation method based on visual-inertial tight coupling | |
| CN108426576A (en) | Aircraft paths planning method and system based on identification point vision guided navigation and SINS | |
| CN110058604A (en) | A kind of accurate landing system of unmanned plane based on computer vision | |
| CN110083177A (en) | A kind of quadrotor and control method of view-based access control model landing | |
| CN107063261A (en) | The multicharacteristic information terrestrial reference detection method precisely landed for unmanned plane | |
| CN114815871A (en) | Vision-based autonomous landing method for vertical take-off and landing unmanned mobile platform | |
| CN116578035A (en) | Rotor unmanned aerial vehicle autonomous landing control system based on digital twin technology | |
| CN114689030A (en) | Unmanned aerial vehicle auxiliary positioning method and system based on airborne vision | |
| Andert et al. | Improving monocular SLAM with altimeter hints for fixed-wing aircraft navigation and emergency landing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |