CN107340711A - A kind of minute vehicle attitude angle automatic testing method based on video image - Google Patents
A kind of minute vehicle attitude angle automatic testing method based on video image Download PDFInfo
- Publication number
- CN107340711A CN107340711A CN201710487641.8A CN201710487641A CN107340711A CN 107340711 A CN107340711 A CN 107340711A CN 201710487641 A CN201710487641 A CN 201710487641A CN 107340711 A CN107340711 A CN 107340711A
- Authority
- CN
- China
- Prior art keywords
- angle
- straight line
- attitude
- parameter
- image
- 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
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/0205—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric not using a model or a simulator of the controlled system
- G05B13/024—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric not using a model or a simulator of the controlled system in which a parameter or coefficient is automatically adjusted to optimise the performance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Automation & Control Theory (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of minute vehicle attitude angle automatic testing method based on video image, mainly comprise the following steps:The image of world cut-off rule is included by forward looking camera shooting;It is determined that the linear equation and its discriminant function of the world cut-off rule relevant with attitude of flight vehicle angle;It is determined that travel through angular range and calculate optimal straight line parameter;The straight line parameter of optimal value is converted into aircraft roll angle φ and pitching angle theta.The present invention is imaged based on forward looking camera, calculated by the parameter optimization of linearity discriminant function, it is extracted into as in, the linear equation parameter of horizontal line, calculating aircraft roll angle and the angle of pitch, optimizing process is improved and optimized herein simultaneously, amount of calculation is drastically reduce the area, suitable for minute vehicle platform of the low cost without attitude measuring.
Description
Technical field
The invention belongs to minute vehicle control technology field, and in particular to a kind of minute vehicle based on video image
Attitude angle automatic testing method.
Background technology
Minute vehicle is a kind of unmanned lightweight flying object of distance type, due to its small volume, in light weight, in natural calamity
The dangerous field tools such as evil detection, the biochemical detection of core, forest fire detection, military surveillance have a broad prospect of the use.But due to it
Load-carrying ability deficiency, the working equipment of carrying is limited, general only to carry microcam and radio transmitting device, and is flying
During need artificial remote control to adjust its flight attitude.
Minute vehicle autonomous flight pose adjustment, dependent on the detection to flight attitude.Horizon (day ground wire) is usual
It is the basis for extracting attitude of flight vehicle.Image horizon detection method more commonly used at present has the following two kinds:
First, made an uproar using automatic threshold segmentation and Hough line detection methods, this method in the more clear nothing of world background
Success rate is higher in the case of sound, but flight uses transmission of wireless signals, can be interfered unavoidably, cause image quality decrease,
Cause a large amount of flase drops.
2nd, using the method for Classification and Identification, mainly by extract image SIFT feature description using SVM be trained with
Identification, this method needs substantial amounts of training data, and hardware realizes complexity, computationally intensive, is not suitable for calculating in real time.
Therefore need to find that a kind of detection is reliable, amount of calculation is small and is easy to hard-wired method, realize high quality, it is low into
This horizon detection.
The content of the invention
The purpose of the present invention is devised and a kind of is based on forward sight precisely in order to realize the automatic correction of the posture of minute vehicle
Video camera imaging, the i.e. horizontal method in world line of demarcation by being extracted into as in, filled suitable for low cost without attitude measurement
The minute vehicle platform put.
The invention provides a kind of minute vehicle attitude angle automatic testing method based on video image, minute vehicle
Forward looking camera is installed, mainly comprised the following steps:
Step 1, forward looking camera shooting image then include sky and ground region in image, at the same image pass through it is wireless
Link passes ground control station back;
It is straight line in above-mentioned image to set world cut-off rule;
Step 2, it is determined that the linear equation of the world cut-off rule relevant with attitude of flight vehicle angle;
Attitude of flight vehicle angle includes roll angle φ and pitching angle theta;
Step 3: determine the discriminant function of the optimal value of the parameter of linear equation;
Step 4: determine traversal angular range;Wherein,
First, set straight line to divide the equilibrium of day ground area, all angular regions of traversal straight line, calculate discriminant function
Value, and the sequence by discriminant score progress from big to small;
Secondly, the relatively low discriminant score that optimized parameter peak value can not possibly occur is excluded, chooses the angle model being likely to occur
Enclose;
Step 5: the angular range in traversal step four, aircraft roll angle is converted to by the straight line parameter of optimal value
φ and pitching angle theta.
The present invention is imaged based on forward looking camera, is calculated by the parameter optimization of linearity discriminant function, is extracted into picture
Middlely, the linear equation parameter of horizontal line, calculating aircraft roll angle and the angle of pitch, while optimizing is improved and optimized herein
Process, amount of calculation is drastically reduce the area, suitable for minute vehicle platform of the low cost without attitude measuring.
Brief description of the drawings
Fig. 1 is the attitude angle overhaul flow chart of the present invention.
Embodiment
The present invention is described in further detail below in conjunction with the accompanying drawings:
It should be noted that the data shown in Figure of description are only a concrete case of checking test of the present invention,
It is for the ease of describing the present invention and helping to understand the spirit of the present invention that it, which is acted on, it is impossible to is understood as being to the technology of the present invention side
The limitation of case.
In the embodiment described once, minute vehicle is provided with forward looking camera, it is preferred to use unmanned rotary wing is miniature
Aircraft carries general visible video camera.A kind of minute vehicle attitude angle automatic detection based on video image of the present invention
Method mainly comprises the following steps:
Step 1, forward looking camera shooting image then include sky and ground region in image, at the same image pass through it is wireless
Link passes ground control station back.
Setting world cut-off rule is straight line in above-mentioned image, and the slope of the straight line is m, intercept b.
Step 2, the linear equation of the world cut-off rule relevant with attitude of flight vehicle angle is determined as follows.
Attitude of flight vehicle angle includes roll angle φ and pitching angle theta,
The relation of arc tangent be present in aircraft roll angle φ and straight slope m:
φ=tan-1(m) (1)。
Using σbThe percentage of whole image shared by the pixel region of straight line the latter half is represented, in forward looking camera shooting
In rectangular image, for ease of calculating, it is assumed that video camera is undistorted after demarcation, then σbIt is linear with pitching angle theta.
Due to pitching angle theta and pixel ratio σbIt is linear, as pixel ratio σbWhen=50%, world region is divided equally in image,
Now the angle of pitch is 0 degree, as pixel ratio σbWhen=100%, image is all ground region, and now pitching angle theta is positive peak
θmax, as pixel ratio σbWhen=0%, image is all sky areas, and now pitching angle theta is negative peak-θmax[6], therefore by taking the photograph
As the pitching angle theta that head measures is calculated as follows:
θ=(1- σb)θmax-σbθmax (2)。
Therefore the linear equation of the present invention uses roll angle angle φ and pixel ratio σbTo represent, it is clear that roll angle angle
φ and pixel ratio σbParameter value scope is
φ ∈ [- pi/2, pi/2], σb∈ [0%, 100%].
Now, linear equation is changed for (φ, σ from original parameter space (m, b)b)。
Step 3: the optimal value of the parameter of linear equation is determined in above-mentioned parameter space by discriminant function.
In the present invention, for sky and the pixel value of ground region, coloured image is judged using RGB numerical value, gray level image
Then utilize gray value.
Sky and ground pixel substantially Gaussian distributed, have straight line to divide the image into heaven and earth two parts, according to
Design criteria, then the difference of the regional average value of two pixels should be larger, while the difference in two regions itself should be smaller,
Here then using itself covariance matrix in both regions.The pixel xi being located on straight linesFor sky areas, under straight lineFor ground pixel, by taking coloured image as an example:
Then both covariance matrixes are represented by:
0 value is likely to occur because both respective covariances calculate, consideration occurs without calculating mistake, adds characteristic vector
Modulus value.Therefore discriminant function J is defined as the modulus value of the covariance determinant plus characteristic value in two regions.
Therefore, optimal function is found to be defined as:
In the range of parameter value, by traveling through all parameters, continuous computational discrimination function J, during value maximum (φ,
σb) it is then the equation of straight line.Due to φ ∈ [- pi/2, pi/2] and σb∈ [0%, 100%], therefore set using i and j when traveling through
Parameter step length, then have:
Step 4: determine traversal angular range.
σ is taken firstb=50%, now namely straight line divides the equilibrium of day ground area, all angular regions of traversal straight line,
Computational discrimination functional value, and the sequence by functional value progress from big to small.
Secondly, the relatively low discriminant score that optimized parameter peak value can not possibly occur is excluded, chooses the angle model being likely to occur
Enclose, finally in whole space search, only travel through these angular ranges, search space can be greatly reduced.Surveyed in actual experiment
In examination, the discriminant score of 20% line number just can determine angular range before selection.
When being most worth search based on formula (10) progress discriminant function parameter, the present invention is without the side for carrying out global traversal i and j
Formula, but i the and j values being likely to occur in pre-selected peak are employed, namely the angular range being likely to occur, it there will not be peak value
Region exclude in advance, finally in whole space search, only travel through these angular ranges being likely to occur, you can guarantee
Maximizing, reduce unnecessary calculating, while eliminate useless search.
Step 5: the angular range in traversal step four, aircraft is converted to by the straight line parameter of optimal value (maximum)
Roll angle φ and pitching angle theta.
It is obvious to a person skilled in the art that the invention is not restricted to the details of above-mentioned one exemplary embodiment, Er Qie
In the case of without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, embodiment all should be regarded as exemplary, and be nonrestrictive, the scope of the present invention is by appended power
Profit requires rather than described above limits, it is intended that all in the implication and scope of the equivalency of claim by falling
Change is included in the present invention.Any reference in claim should not be considered as to the involved claim of limitation.
Moreover, it will be appreciated that although the present specification is described in terms of embodiments, not each embodiment is only wrapped
Containing an independent technical scheme, this narrating mode of specification is only that those skilled in the art should for clarity
Using specification as an entirety, the technical solutions in the various embodiments may also be suitably combined, forms those skilled in the art
It is appreciated that other embodiment.
The description to embodiment the invention is not restricted to more than, those skilled in the art according to disclosure of the present invention,
The creative work improvement and modification that be carried out need not be passed through on the basis of the present invention, all should protection scope of the present invention it
It is interior.
Claims (1)
1. a kind of minute vehicle attitude angle automatic testing method based on video image, minute vehicle is provided with forward sight shooting
Machine, it is characterised in that mainly comprise the following steps:
Step 1, forward looking camera shooting image, sky and ground region is then included in image;
It is straight line in above-mentioned image to set world cut-off rule;
Step 2, it is determined that the linear equation of the world cut-off rule relevant with attitude of flight vehicle angle;
Attitude of flight vehicle angle includes roll angle φ and pitching angle theta;
Step 3: determine the discriminant function of the optimal value of the parameter of linear equation;
Step 4: determine traversal angular range;Wherein,
First, set straight line to divide the equilibrium of day ground area, all angular regions of traversal straight line, calculate discriminant score,
And the sequence by discriminant score progress from big to small;
Secondly, the relatively low discriminant score that optimized parameter peak value can not possibly occur is excluded, chooses the angular range being likely to occur;
Step 5: the angular range in traversal step four, by the straight line parameter of maximum occurrences be converted to aircraft roll angle φ and
Pitching angle theta.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710487641.8A CN107340711A (en) | 2017-06-23 | 2017-06-23 | A kind of minute vehicle attitude angle automatic testing method based on video image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710487641.8A CN107340711A (en) | 2017-06-23 | 2017-06-23 | A kind of minute vehicle attitude angle automatic testing method based on video image |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107340711A true CN107340711A (en) | 2017-11-10 |
Family
ID=60221006
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710487641.8A Pending CN107340711A (en) | 2017-06-23 | 2017-06-23 | A kind of minute vehicle attitude angle automatic testing method based on video image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107340711A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113551663A (en) * | 2021-06-21 | 2021-10-26 | 北京理工大学 | Image and geomagnetism combined aircraft attitude calculation system and method |
CN116242322A (en) * | 2023-05-11 | 2023-06-09 | 开拓导航控制技术股份有限公司 | Object rolling gesture detection method, device and system |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102163334A (en) * | 2011-03-04 | 2011-08-24 | 北京航空航天大学 | Method for extracting video object under dynamic background based on fisher linear discriminant analysis |
CN103453875A (en) * | 2013-08-07 | 2013-12-18 | 北京理工大学 | Real-time calculating method for pitch angle and roll angle of unmanned aerial vehicle |
CN103697883A (en) * | 2014-01-07 | 2014-04-02 | 中国人民解放军国防科学技术大学 | Aircraft horizontal attitude determination method based on skyline imaging |
CN104778695A (en) * | 2015-04-10 | 2015-07-15 | 哈尔滨工程大学 | Water sky line detection method based on gradient saliency |
US20160012316A1 (en) * | 2014-07-10 | 2016-01-14 | King Fahd University Of Petroleum And Minerals | Method, system and computer program product for breast density classification using fisher discrimination |
CN105644785A (en) * | 2015-12-31 | 2016-06-08 | 哈尔滨工业大学 | Unmanned aerial vehicle landing method based on optical flow method and horizon line detection |
CN105787950A (en) * | 2016-03-24 | 2016-07-20 | 电子科技大学 | Infrared image sea-sky-line detection algorithm based on line gradient accumulation |
CN106534709A (en) * | 2015-09-10 | 2017-03-22 | 鹦鹉无人机股份有限公司 | Drone with a front-view camera with segmentation of the sky image for auto-exposure control |
-
2017
- 2017-06-23 CN CN201710487641.8A patent/CN107340711A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102163334A (en) * | 2011-03-04 | 2011-08-24 | 北京航空航天大学 | Method for extracting video object under dynamic background based on fisher linear discriminant analysis |
CN103453875A (en) * | 2013-08-07 | 2013-12-18 | 北京理工大学 | Real-time calculating method for pitch angle and roll angle of unmanned aerial vehicle |
CN103697883A (en) * | 2014-01-07 | 2014-04-02 | 中国人民解放军国防科学技术大学 | Aircraft horizontal attitude determination method based on skyline imaging |
US20160012316A1 (en) * | 2014-07-10 | 2016-01-14 | King Fahd University Of Petroleum And Minerals | Method, system and computer program product for breast density classification using fisher discrimination |
CN104778695A (en) * | 2015-04-10 | 2015-07-15 | 哈尔滨工程大学 | Water sky line detection method based on gradient saliency |
CN106534709A (en) * | 2015-09-10 | 2017-03-22 | 鹦鹉无人机股份有限公司 | Drone with a front-view camera with segmentation of the sky image for auto-exposure control |
CN105644785A (en) * | 2015-12-31 | 2016-06-08 | 哈尔滨工业大学 | Unmanned aerial vehicle landing method based on optical flow method and horizon line detection |
CN105787950A (en) * | 2016-03-24 | 2016-07-20 | 电子科技大学 | Infrared image sea-sky-line detection algorithm based on line gradient accumulation |
Non-Patent Citations (8)
Title |
---|
S.M. ETTINGER等: "Vision-guided flight stability and control for micro air vehicles", 《IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS》 * |
于玉林主编: "《中国大百科全书出版社》", 30 November 1994 * |
周宇等: "微小型飞行器视觉导航中两种图像分割方法的比较研究", 《2006航空宇航科学与技术全国博士生学术论坛论文集》 * |
李克庆编: "《数学地质》", 30 October 2015 * |
王佐仁主编: "《调查培训实用教材 下 统计数据分析方法》", 30 June 2011 * |
赵世峰等: "一种基于计算机视觉的飞行器姿态估计算法", 《北京航空航天大学学报》 * |
高爱民: "一种基于视觉的微型飞行器姿态检测算法", 《飞机设计》 * |
黄英东等: "一种基于图像信息的微小型飞行器姿态测量方法", 《弹箭与制导学报》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113551663A (en) * | 2021-06-21 | 2021-10-26 | 北京理工大学 | Image and geomagnetism combined aircraft attitude calculation system and method |
CN113551663B (en) * | 2021-06-21 | 2024-03-19 | 北京理工大学 | System and method for resolving aircraft attitude by combining images and geomagnetism |
CN116242322A (en) * | 2023-05-11 | 2023-06-09 | 开拓导航控制技术股份有限公司 | Object rolling gesture detection method, device and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113359810B (en) | Unmanned aerial vehicle landing area identification method based on multiple sensors | |
CN105512628B (en) | Vehicle environmental sensory perceptual system based on unmanned plane and method | |
CN108919838B (en) | Binocular vision-based automatic tracking method for power transmission line of unmanned aerial vehicle | |
CN107830846B (en) | Method for measuring angle of communication tower antenna by using unmanned aerial vehicle and convolutional neural network | |
US9805293B2 (en) | Method and apparatus for object recognition in image processing | |
CN109739254B (en) | Unmanned aerial vehicle adopting visual image positioning in power inspection and positioning method thereof | |
CN105318888A (en) | Unmanned perception based unmanned aerial vehicle route planning method | |
CN104933708A (en) | Barrier detection method in vegetation environment based on multispectral and 3D feature fusion | |
CN105241423B (en) | A kind of evaluation method based on unmanned plane photogram to high canopy density Stand Volume | |
CN109063532B (en) | Unmanned aerial vehicle-based method for searching field offline personnel | |
CN110991502B (en) | Airspace security situation assessment method based on category activation mapping technology | |
CN107450586B (en) | Method and system for adjusting air route and unmanned aerial vehicle system | |
CN111709994B (en) | Autonomous unmanned aerial vehicle visual detection and guidance system and method | |
CN112947526B (en) | Unmanned aerial vehicle autonomous landing method and system | |
Shen et al. | Person tracking and frontal face capture with uav | |
CN107221006A (en) | A kind of communication single pipe tower slant detection method based on unmanned plane imaging platform | |
CN105243653A (en) | Fast mosaic technology of remote sensing image of unmanned aerial vehicle on the basis of dynamic matching | |
CN111831010A (en) | Unmanned aerial vehicle obstacle avoidance flight method based on digital space slice | |
CN107340711A (en) | A kind of minute vehicle attitude angle automatic testing method based on video image | |
CN112435298A (en) | Jet flow closed-loop control method based on image processing and monocular vision | |
CN108563986B (en) | Method and system for judging posture of telegraph pole in jolt area based on long-distance shooting image | |
CN116486290B (en) | Unmanned aerial vehicle monitoring and tracking method and device, electronic equipment and storage medium | |
CN112818964A (en) | Unmanned aerial vehicle detection method based on FoveaBox anchor-free neural network | |
CN109461179B (en) | Cooperative detection system for explosive-handling primary and secondary robots | |
CN117409339A (en) | Unmanned aerial vehicle crop state visual identification method for air-ground coordination |
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: 20171110 |