CN105809700B - A kind of drogue image detection localization method blocked by oily plug - Google Patents
A kind of drogue image detection localization method blocked by oily plug Download PDFInfo
- Publication number
- CN105809700B CN105809700B CN201610168310.3A CN201610168310A CN105809700B CN 105809700 B CN105809700 B CN 105809700B CN 201610168310 A CN201610168310 A CN 201610168310A CN 105809700 B CN105809700 B CN 105809700B
- Authority
- CN
- China
- Prior art keywords
- image
- circumference
- tapered sleeve
- blocked
- profile
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 41
- 238000000034 method Methods 0.000 title claims abstract description 41
- 230000004807 localization Effects 0.000 title claims abstract description 17
- 239000000945 filler Substances 0.000 claims abstract description 16
- 238000006243 chemical reaction Methods 0.000 claims description 23
- 230000002093 peripheral effect Effects 0.000 claims description 14
- 238000000605 extraction Methods 0.000 claims description 8
- 230000000903 blocking effect Effects 0.000 claims description 5
- 241000196324 Embryophyta Species 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 3
- 239000012141 concentrate Substances 0.000 claims 1
- 238000005260 corrosion Methods 0.000 claims 1
- 230000007797 corrosion Effects 0.000 claims 1
- 238000012545 processing Methods 0.000 abstract description 4
- 239000000446 fuel Substances 0.000 description 14
- 230000004438 eyesight Effects 0.000 description 7
- 230000003287 optical effect Effects 0.000 description 5
- 238000009432 framing Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000005530 etching Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
- G06T5/75—Unsharp masking
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of drogue image detection localization method blocked by oily plug, belong to the technical field of Computer Image Processing.The present invention quickly rejects the interference such as umbrella frame, the hose on internal black circle oil filler periphery in tapered sleeve image using Mathematical Morphology Method, then judge to obtain the image-region where the oil filler of tapered sleeve inside with rejectings, subcircular shape condition judgment etc. by contours extract, occlusion area registration, calculating process is simple, can quickly detect tapered sleeve picture position and region of the positioning under by oily plug circumstance of occlusion.
Description
Technical field
The invention discloses a kind of drogue image detection localization methods blocked by oily plug, belong to computer
The technical field of image procossing.
Background technology
Existing most of autonomous air refuelling vision navigation methods are mounted on to refuel frequently with special optical markings and bore
It puts on, marked including LED light mark, artificial special color etc..It has been used if in the autonomous air refuelling project (AAR) in the U.S. a set of
VisNav systems, the VisNav systems are just needed to install multiple LED light marks on fuel filling taper sleeve, then visited using semiconductor position
Survey device PSD carry out framing (see Dong new people, Xu Yuejian, Chen Bo,《Automatic air refuelling Research progress is asked with key
Topic》,《Air force engineering college journal (natural science edition)》, 2008 (12), 9 (6):1-5).In addition, domestic air force engineering university
Wang Xufeng etc. establishes a vision Relative Navigation semi physical ground experiment platform of autonomous air refuelling, and breaks in fuel filling taper sleeve
Face region has installed red identification rings band additional, with Enhanced feature region and the contrast of background image, so as to pass through color recognition
Obtain framing information (see Wang Xufeng, Dong new people, Kong Xingwei,《The plug taper sleeve type unmanned plane of machine vision auxiliary is independently empty
Middle emulation of refueling》,《Science and technology and engineering》, 2013 (6), 13 (18):5245-5250).
Above-mentioned these methods requirement fuel filling taper sleeve installs additional optical markings, is carried in particular for the LED light mark of power supply
The high risk of air-refueling operation.Therefore it is a kind of not against additional markers, merely with the AAR visions of fuel filling taper sleeve feature itself
Method just has better versatility, convenience and security.
Passing through the analysis to fuel filling taper sleeve shape feature, it is known that its internal oil filler is circular, and radius is about 13cm, into
Apparent black round block or subcircular oval block is presented in the picture as after, therefore can using this apparent own form feature
Reduce the calculation amount of framing processing.With the development of unmanned plane, the demand of autonomous air refuelling is also just more and more urgent, and
There is higher versatility and convenience, particularly base not against the autonomous air refuelling vision navigation method of extra optical mark
Apparent in the computer vision methods feature of fuel filling taper sleeve inner circular oil filler, image processing speed is fast, and often camera
It is mounted in by oily plug side rear, fuel filling taper sleeve can be formed and blocked as display foreground object by oily plug, solved by oil
The fuel filling taper sleeve image detection positioning that plug is blocked under interference is the key that autonomous air refuelling vision guided navigation, and this programme is base
It is generated in foregoing thinking.
The content of the invention
The technical problems to be solved by the invention are to need installation additional in existing autonomous air refuelling method is overcome
Insufficient, the additional Charging system of optical markings brings higher air refuelling danger etc., from relying only on fuel filling taper sleeve itself
Feature solves to be set out by the angle of oily plug image occlusion issue in vision guided navigation, provides a kind of sky blocked by oily plug
Middle fuel filling taper sleeve image detection localization method, this method quickly reject internal black in tapered sleeve image using Mathematical Morphology Method
The interference such as umbrella frame, the hose on circular oil filler periphery are then judged with rejecting, closely by contours extract, occlusion area registration
Toroidal condition judgment etc. obtains the image-region where oil filler inside tapered sleeve.
The present invention adopts the following technical scheme that for achieving the above object:
A kind of drogue image detection localization method blocked by oily plug, includes the following steps:
A, reversed binary conversion treatment is carried out to the mask images blocked by oily plug, to the mask after reversed binary conversion treatment
Image carries out mathematical morphology closed operation and obtains the first binary mask image, and mathematical morphology is carried out to the first binary mask image
Etching operation obtains the second binary mask image;
B, reversed binary conversion treatment is carried out to tapered sleeve gray level image to be detected;
C, the mask images blocked to the tapered sleeve gray level image to be detected after reversed binary conversion treatment and by oily plug carry out
Or computing, pair or the bianry image that obtains of computing carry out mathematical morphology and open operation to obtain bianry image;
D, contours extract is carried out to the bianry image that step C is obtained and obtains circumference, the set put on each circumference
Form circumference edge point set;
E, the area descending that each profile surrounds is arranged, filters out the circumference less than contour area threshold value, will screen
The set put on the circumference gone out is concentrated from circumference marginal point and rejected;
F, the judgement of block masks registration is carried out to the circumference that screening leaves, F1 is entered step when misaligned, weight
F2 is entered step during conjunction,
F1, circumference is directly carried out to include regional extent constraint, circularity constraint, least square ellipse
The nearly circle target detection of fitting condition constraint, retains the objective contour for meeting nearly circle target detection requirement,
F2, circumference is carried out to block nearly circle target detection, retains the target for meeting and blocking nearly circle target detection requirement
Profile:It rejects first in circumference and blocks interference, the circumference then blocked to rejecting after interference carries out including region
Range of condition constraint, the nearly circle target detection of least square ellipse fitting condition constraint;
G, record the ellipse fitting parameter of each candidate target profile and calculate the logarithm circularity of each fitted ellipse, selection pair
Final image positioning result of the candidate target profile of number circularity maximum as oil filler inside tapered sleeve.
As a kind of further optimization side of the drogue image detection localization method blocked by oily plug
Case, step B use expression formula:Tapered sleeve gray level image to be detected is carried out reversed
Binary conversion treatment,
Wherein, (x, y) represents image pixel coordinates, B0(x, y) represents the tapered sleeve to be detected ash after reversed binary conversion treatment
Image is spent in the grey scale pixel value of (x, y) position, Dorigin(x, y) represents picture of the tapered sleeve gray level image to be detected in (x, y) position
Plain gray value, T1Represent the threshold value of reversed binary conversion treatment tapered sleeve gray level image to be detected.
Further, a kind of drogue image detection localization method blocked by oily plug, it is right in step F
The judgement that the circumference left carries out block masks registration is screened, specific method is:
The mask images after anterior peripheral contour area bianry image and reversed binary conversion treatment to extraction are done and computing
To extract interested subgraph,
Count the number of pixels that block masks area pixel value is identical in the subgraph:
When the number of pixels of statistics is more than given threshold, anterior peripheral contour area and block masks region weight are judged
It closes,
When the number of pixels of statistics is less than or equal to given threshold, anterior peripheral contour area and block masks area are judged
Domain is misaligned.
Further, a kind of drogue image detection localization method blocked by oily plug, step F2
Interference is blocked in middle rejecting circumference, specific method is:
Circumference region bianry image to extraction and the first binary mask image is done and computing, pair with the figure after computing
Open operation as carrying out mathematical morphology, extraction is opened operate after bianry image profile to obtain the point set of anterior peripheral profile, pick
Remove anterior peripheral profile point concentration and the point of the second binary mask picture registration.
Further, the step F2 of a kind of drogue image detection localization method blocked by oily plug
In,
The regional extent condition is:(xd>T3)&(yd>T3)&(yd>T41·xd)&(xd>T41·yd),
The least square ellipse fitting condition is:{2a>T3}&{2b>T3}&{a>T41·b}&{b>T41A } andWherein,
(xk1,yk1)、(xk2,yk2)、……、The 1st on respectively k-th of candidate target profile, the 2nd ..., n-thkA point
Pixel coordinate, T3For regional extent threshold value, T41For regional percentage threshold value, & represents logical AND operation, and (a, b) is fitted ellipse
Long semi-minor axis,For setAverage value and standard deviation, T6For error of fitting average threshold value, T7
For fit error criterion difference threshold value,
(xc,yc) be fitted ellipse center point coordinate, θ be fitted ellipse rotation angle.
As a kind of further optimization of the drogue image detection localization method blocked by oily plug
Scheme, the expression formula that fitted ellipse logarithm circularity f (a, b) is calculated in step G are:
The present invention is had the advantages that using above-mentioned technical proposal:
(1) optical markings on fuel filling taper sleeve need not be additionally installed, merely with fuel filling taper sleeve unique characteristics, had more preferable
Versatility, convenience and security;
(2) this method is carried for the fuel filling taper sleeve image detection under by oily plug circumstance of occlusion using binaryzation rear profile
The method taken quickly determines target area to be detected, pair is disappeared with the profile of block masks area coincidence by the way of mask rejecting
Except the image disruption brought is blocked by oily plug, profile where determining whether target eventually by contour shape, this method is thought
Road is clear, and calculating process is simple, can quickly detect tapered sleeve picture position and region of the positioning under by oily plug circumstance of occlusion.
Description of the drawings
Fig. 1 is the calculation flow chart of the method for the present invention;
Fig. 2 is the original tapered sleeve coloured image of acquisition;
Fig. 3 is reversely by oily plug block masks image;
Fig. 4 is tapered sleeve binary image and the bianry image after mask images or operation;
Fig. 5 is that morphology opens the tapered sleeve bianry image after operation;
Fig. 6 is the contours extract result rejected after small area profile;
Fig. 7 is the contour area bianry image overlapped with masks area;
Fig. 8 is that Fig. 7 bianry images reject the contours extract result after masks area;
Fig. 9 weeds out the result after the profile point overlapped with masks area for Fig. 8 profiles;
Figure 10 is oil filler image detection positioning result inside final tapered sleeve.
Specific embodiment
The technical solution of invention is described in detail below in conjunction with the accompanying drawings.
A kind of drogue image detection localization method blocked by oily plug, merely with fuel filling taper sleeve therein
Circular oil filler feature, it is quick to reject internal dark circles in tapered sleeve image by carrying out mathematical morphology operation to bianry image
Shape oil filler periphery is disturbed, then on the basis of contours extract, using in by the judgement of oily plug mask images and rejecting profile
Shield portions, and be quickly obtained using subcircular shape condition the subcircular profile of candidate, finally select logarithm circularity maximum
Candidate solution as tapered sleeve image detection positioning result.Specifically include following steps.
The mask images that step 1, preparation are blocked by oily plug:It is hidden in the mask images M blocked by oily plug by oily plug
Gear area pixel value is set to 0, and other regions are set to 1;Reversed mask images are calculated, i.e. occlusion area pixel value is 1, Qi Taqu
Domain is 0, and the mask images after reversed binary conversion treatment are denoted as Mi;Radius is used as r1Disc-shape structural element DrTo by oil
The mask images M that plug blocks carries out mathematical morphology closed operation, obtains the first binary mask image Mc;Radius is used as r1's
Disc-shape structural element DrTo image McMathematical morphology etching operation is carried out, obtains the second binary mask image Me, r1Value
Scope is 3~12, uses radius as r1Disc-shape structural element DrMathematical morphology operation is carried out to image can expand area
Domain scope.
Step 2 is loaded into tapered sleeve gray level image D to be detectedorigin, using threshold value T1To image DoriginReversed binaryzation,
Obtain the tapered sleeve gray level image B to be detected after reversed binary conversion treatment0.Specific conversion process is as follows:
In formula, T1Represent the threshold value of reversed binary conversion treatment tapered sleeve gray level image to be detected, (x, y) represents that image pixel is sat
Mark, Dorigin(x, y) and B0(x, y) represents tapered sleeve gray level image D to be detected respectivelyoriginWith treating after reversed binary conversion treatment
Detect tapered sleeve gray level image B0Grey scale pixel value at position (x, y).
Tapered sleeve gray level image B to be detected after step 3, reversed binary conversion treatment0With the mask images M blocked by oily plug
It carries out or operates, obtain bianry image B1, radius is used as r1Disc-shape structural element DrTo bianry image B1Carry out mathematics
Morphology opens operation, obtains bianry image B2。
Step 4, to bianry image B2Contours extract operation is carried out, obtains circumference edge point setWherein, N1Represent profile number, Ck(k=1,2 ..., N1) represent what is put on each profile
Set, is represented byN in formulakRepresent contour edge point number.
The area of each profile, note profile C in step 5, statistics contour edge point set CkArea be sk, to sequenceDescending arrangement is carried out, and weeds out area less than T2The profile of (contour area threshold value), T2Selection range be
60~200, it is final to obtain the profile number of area from big to small, it is denoted asMeet following formula:
Step 6 puts mark fmask=0, successively to numbering set d={ d1,d2,...,dmIn each profile carry out such as
Lower processing:
It is d for current numberjThe profile of=k, j=1,2 ..., m,
If fmask=0, then 7 are entered step, block masks registration judgement is carried out to current outline, if judging result is attached most importance to
It closes, then puts fmask=1, and 8 are entered step, it carries out blocking nearly circle target detection, records testing result;If judging result is not weigh
It closes, then enters step 9, nearly circle target detection operation is directly carried out to current outline, records testing result,
If fmask=1, step 9 is directly entered, nearly circle target detection operation is carried out to current outline, records testing result,
After the completion of all profiles are handled, 10 are entered step.
Step 7, block masks registration judge:Judge current number for dj=k, j=1,2 ..., the profile of m whether with
By oily plug block masks area coincidence.
Step 701, extraction anterior peripheral contour area bianry image C0, contour area pixel value is set to 1, and other regions are set
For 0,
Step 702, anterior peripheral contour area bianry image C0With the mask images M after reversed binary conversion treatmentiIt carries out
With operation obtains bianry image C1,
Step 703, statistics bianry image C1Middle pixel value is 1 number of pixels, if number of pixels is more than threshold value TN, then sentence
Disconnected current outline region with by oily plug block masks area coincidence;Otherwise judge misaligned.
Step 8 blocks nearly circle target detection:To meeting the anterior peripheral contour area of block masks registration Rule of judgment
Bianry image carries out blocking nearly circle target detection judgement.
Step 801, the anterior peripheral contour area bianry image C by extraction0With the first binary mask image McCarry out "AND"
Operation obtains bianry image C2,
Step 802 uses radius as r2Disc-shape structural element DrTo bianry image C2It carries out mathematical morphology and opens behaviour
Make, obtain bianry image C3, r2Value range is 3~6, uses radius as r2Disc-shape structural element to image into line number
Morphology, which opens operation, can reject the interference such as umbrella frame.
Step 803, to bianry image C3Contours extract operation is carried out, circumference point set is obtained, and weeds out all wheels
Exterior feature point is concentrated and the second binary mask image MeThe point of coincidence,
Step 804 enters step 9, nearly circle target detection operation is carried out to each profile, wherein using new regional percentage
Threshold value T4=T41, and without circularity condition judgment, T41Value range is 0.35~0.95.
Step 9, closely round target detection:To profile point setRepresented profile carries out nearly circle mesh
Mark judges.
Step 901, candidate target profile must are fulfilled for following region range of condition:
Calculate the scope (x of profile point set image coordinated,yd) as follows:
Regional extent condition is:
(xd>T3)&(yd>T3)&(yd>T4·xd)&(xd>T4·yd),
In formula, T3For regional extent threshold value, T4For regional percentage threshold value, & represents logical AND operation, T3Selection range for 7~
15, T4Selection range is 0.5~0.95.
Step 902, candidate target profile must are fulfilled for following circularity condition:
In formula, T5For circularity threshold value, T5Selection range is 0.60~0.95, lkFor the week of k-th of candidate target profile
It is long.
Step 903, candidate target profile must are fulfilled for following least square ellipse fitting condition:
(1) least square ellipse is fitted:Using least square method to point setCarry out oval plan
It closes, fitting result is denoted as (xc,yc, a, b, θ), wherein (xc,yc) for elliptical center point coordinates, (a, b) is oval long semi-minor axis, θ
For ELLIPTIC REVOLUTION angle.
(2) oval magnitude range judges:Candidate target profile must is fulfilled for following condition:
{2a>T3}&{2b>T3}&{a>T4·b}&{b>T4·a}
(3) range error is fitted to judge:Calculate point setTo the range error e of fitted ellipseiSuch as
Under:
In formula, (exi,eyi) it is the oval point coordinates of standardization, it can be calculated as follows:
Candidate target profile must is fulfilled for following condition:
In formula, T6For error of fitting average threshold value, T7For fit error criterion difference threshold value,For setAverage value and standard deviation, T6Selection range is 0.01~0.10, T7Selection range is 0.01~0.10.
Step 10, record meet the ellipse fitting parameter of the candidate region of above-mentioned condition, and it is circular to calculate elliptical logarithm
DegreeSelect final image positioning of the candidate solution of logarithm circularity maximum as oil filler inside tapered sleeve
As a result.
Fig. 2 is the original tapered sleeve coloured image of acquisition, and number of pixels is 640 × 480.After being converted to gray level image, use
The method of the present invention handles tapered sleeve gray level image, sets relevant parameter as follows:
T1=75, r1=8, r2=3, T2=300, T3=9, T4=0.707, T41=0.4, T5=0.65, T6=0.05, T7
=0.03
Fig. 3 be it is reversed by oily plug block masks image, Fig. 4 is the bianry image after tapered sleeve image binaryzation, can be with
Internal oil filler periphery be will become apparent from there are interference such as umbrella frame, backgrounds, and blocked by the formation of oily plug;Fig. 4 is tapered sleeve two-value
Change image and the bianry image after mask images or operation;Fig. 5 is that morphology opens the tapered sleeve bianry image after operation, and tapered sleeve refuels
The interference of mouth periphery has been isolated with oil filler region;Fig. 6 is the contours extract result rejected after small area profile;Fig. 7 is with covering
The contour area bianry image of mould area coincidence;Fig. 8 is that Fig. 7 bianry images reject the contours extract result after masks area;Fig. 9
The result after the profile point overlapped with masks area is weeded out for Fig. 8 profiles, it can be seen that profile point is disturbed caused by blocking
It has been removed;Figure 10 is oil filler image detection positioning result inside final tapered sleeve, it can be seen that detection positioning result with
Tapered sleeve inner circular oil filler essentially coincides.The above results demonstrate the correctness of the method for the present invention.
Claims (6)
1. a kind of drogue image detection localization method blocked by oily plug, which is characterized in that include the following steps:
A, reversed binary conversion treatment is carried out to the mask images blocked by oily plug, to the mask images after reversed binary conversion treatment
It carries out mathematical morphology closed operation and obtains the first binary mask image, mathematical morphology corrosion is carried out to the first binary mask image
Operation obtains the second binary mask image;
B, reversed binary conversion treatment is carried out to tapered sleeve gray level image to be detected;
C, the mask images blocked to the tapered sleeve gray level image to be detected after reversed binary conversion treatment and by oily plug are carried out or transported
Calculate, pair or the bianry image that obtains of computing carry out mathematical morphology and open operation to obtain bianry image;
D, contours extract is carried out to the bianry image that step C is obtained and obtains circumference, the set put on each circumference is formed
Circumference edge point set;
E, the area descending that each profile surrounds is arranged, the circumference less than contour area threshold value is filtered out, by what is filtered out
The set put on circumference is concentrated from circumference marginal point and rejected;
F, the judgement of block masks registration is carried out to the circumference that leaves of screening, enters step F1 when misaligned, during coincidence
Enter step F2,
F1, circumference is directly carried out to include regional extent constraint, circularity constraint, least square ellipse fitting
The nearly circle target detection of constraint, retains the objective contour for meeting nearly circle target detection requirement,
F2, circumference is carried out to block nearly circle target detection, retains the objective contour for meeting and blocking nearly circle target detection requirement:
It rejects first in circumference and blocks interference, the circumference then blocked to rejecting after interference carries out including regional extent item
Part constraint, the nearly circle target detection of least square ellipse fitting condition constraint;
G, record the ellipse fitting parameter of each candidate target profile and calculate the logarithm circularity of each fitted ellipse, select logarithm circle
Final image positioning result of the candidate target profile of shape degree maximum as oil filler inside tapered sleeve.
2. a kind of drogue image detection localization method blocked by oily plug according to claim 1, feature
It is, step B uses expression formula:Tapered sleeve gray level image to be detected is carried out anti-
To binary conversion treatment,
Wherein, (x, y) represents image pixel coordinates, B0(x, y) represents the tapered sleeve gray level image to be detected after reversed binary conversion treatment
Grey scale pixel value in (x, y) position, Dorigin(x, y) represents pixel grey scale of the tapered sleeve gray level image to be detected in (x, y) position
Value, T1Represent the threshold value of reversed binary conversion treatment tapered sleeve gray level image to be detected.
3. a kind of drogue image detection localization method blocked by oily plug according to claim 2, feature
It is, carry out the judgement of block masks registration in step F to the circumference that screening leaves, specific method is:
The mask images after anterior peripheral contour area bianry image and reversed binary conversion treatment to extraction are done with computing to carry
Interested subgraph is taken,
Count the number of pixels that block masks area pixel value is identical in the subgraph:
When the number of pixels of statistics is more than given threshold, anterior peripheral contour area and block masks area coincidence are judged,
When the number of pixels of statistics is less than or equal to given threshold, judge that anterior peripheral contour area is not weighed with block masks region
It closes.
4. a kind of drogue image detection localization method blocked by oily plug according to claim 3, feature
It is, is rejected in step F2 in circumference and block interference, specific method is:
Circumference region bianry image to extraction and the first binary mask image is done and computing, pair with the image after computing into
Row mathematical morphology opens operation, and extraction opens the profile of bianry image after operation to obtain the point set of anterior peripheral profile, weeds out
Anterior peripheral profile point concentrates the point with the second binary mask picture registration.
5. according to arbitrary a kind of drogue image detection positioning side blocked by oily plug in Claims 1-4
Method, which is characterized in that in step F2,
The regional extent condition is:(xd>T3)&(yd>T3)&(yd>T41·xd)&(xd>T41·yd),
The least square ellipse fitting condition is:{2a>T3}&{2b>T3}&{a>T41·b}&{b>T41A } and
Wherein,
The 1st on respectively k-th of candidate target profile, the 2nd ..., n-thkThe pixel coordinate of a point, T3For regional extent threshold value, T41
For regional percentage threshold value, logical AND operation is represented, (a, b) is the long semi-minor axis of fitted ellipse,For setAverage value and standard deviation, T6For error of fitting average threshold value, T7For fit error criterion difference threshold value,
(xc,yc) be fitted ellipse center point coordinate, θ be fitted ellipse rotation angle.
6. a kind of drogue image detection localization method blocked by oily plug according to claim 5, feature
It is, the expression formula that fitted ellipse logarithm circularity f (a, b) is calculated in step G is:
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610168310.3A CN105809700B (en) | 2016-03-23 | 2016-03-23 | A kind of drogue image detection localization method blocked by oily plug |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610168310.3A CN105809700B (en) | 2016-03-23 | 2016-03-23 | A kind of drogue image detection localization method blocked by oily plug |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105809700A CN105809700A (en) | 2016-07-27 |
CN105809700B true CN105809700B (en) | 2018-06-01 |
Family
ID=56454714
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610168310.3A Active CN105809700B (en) | 2016-03-23 | 2016-03-23 | A kind of drogue image detection localization method blocked by oily plug |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105809700B (en) |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107194045B (en) * | 2017-05-08 | 2020-08-14 | 北京航空航天大学 | Modeling method for front disturbance wave of oil receiving machine for air refueling |
CN107464259B (en) * | 2017-06-21 | 2020-10-20 | 南京航空航天大学 | Target detection method based on taper sleeve edge feature modeling |
CN111815726B (en) * | 2020-07-09 | 2021-08-10 | 深圳企业云科技股份有限公司 | Ellipse angle coding and decoding method based on computer vision recognition system |
CN114081478A (en) * | 2021-11-26 | 2022-02-25 | 河南九州网络科技有限公司 | Motion state dynamic monitoring terminal and user identity judgment method |
CN114387274B (en) * | 2022-03-24 | 2022-06-03 | 武汉昊月纸箱包装有限公司 | Carton defect detection method based on artificial intelligence |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103557792A (en) * | 2013-11-12 | 2014-02-05 | 中国科学院自动化研究所 | Method for visual tracking and position measurement of drogue object |
CN104460505A (en) * | 2014-11-12 | 2015-03-25 | 沈阳新松机器人自动化股份有限公司 | Industrial robot relative pose estimation method |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7681839B2 (en) * | 2005-02-25 | 2010-03-23 | Smiths Aerospace Llc | Optical tracking system for refueling |
-
2016
- 2016-03-23 CN CN201610168310.3A patent/CN105809700B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103557792A (en) * | 2013-11-12 | 2014-02-05 | 中国科学院自动化研究所 | Method for visual tracking and position measurement of drogue object |
CN104460505A (en) * | 2014-11-12 | 2015-03-25 | 沈阳新松机器人自动化股份有限公司 | Industrial robot relative pose estimation method |
Non-Patent Citations (6)
Title |
---|
《加油锥套远距图像的Hough-LS快速检测》;杨博文 等;《光电工程》;20150430;第42卷(第4期);第44-48页 * |
《基于Kalman预测的空中加油锥套跟踪方法》;周晓达 等;《数据采集与处理》;20141130;第29卷(第6期);第1041-1045页 * |
《基于双目视觉的自主空中加油算法研究与仿真》;纪超 等;《系统仿真学报》;20130630;第25卷(第6期);第1327-1331页 * |
《自主空中加油视觉导航系统中的锥套检测算法》;宋春华 等;《红外与激光工程》;20130430;第42卷(第4期);第1089-1094页 * |
《视觉辅助的无人机自主空中加油建模与仿真》;王旭峰 等;《飞行力学》;20130831;第31卷(第4期);第331-335页 * |
《迭代最小二乘椭圆拟合的锥套图像检测与跟踪》;黄斌 等;《中国图象图形学报》;20140831;第19卷(第8期);第1202-1209页 * |
Also Published As
Publication number | Publication date |
---|---|
CN105809700A (en) | 2016-07-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105809700B (en) | A kind of drogue image detection localization method blocked by oily plug | |
CN105825515B (en) | A kind of fuel filling taper sleeve image detection localization method for autonomous air refuelling | |
CN111259892B (en) | Inspection method, inspection device, inspection equipment and inspection medium for state of indicator lamp | |
CN104778721B (en) | The distance measurement method of conspicuousness target in a kind of binocular image | |
CN105809138A (en) | Road warning mark detection and recognition method based on block recognition | |
CN104809433B (en) | A kind of zebra line detecting method based on maximum stable region and stochastical sampling | |
CN104134209B (en) | A kind of feature extracting and matching method and system in vision guided navigation | |
CN108154082A (en) | The method and system of the automatic object detecting of aerial images | |
CN110232389A (en) | A kind of stereoscopic vision air navigation aid based on green crop feature extraction invariance | |
CN107330376A (en) | A kind of Lane detection method and system | |
CN110414400B (en) | Automatic detection method and system for wearing of safety helmet on construction site | |
CN107063261B (en) | Multi-feature information landmark detection method for precise landing of unmanned aerial vehicle | |
CN103413124B (en) | A kind of circular traffic sign detection method | |
CN106225787A (en) | Unmanned aerial vehicle visual positioning method | |
CN107506760A (en) | Traffic signals detection method and system based on GPS location and visual pattern processing | |
CN103886285A (en) | Method for detecting optical remote-sensing image ship with assistance of prior geographic information | |
CN102938057B (en) | A kind of method for eliminating vehicle shadow and device | |
CN101226637B (en) | Method for detecting automatically contact point of vehicle wheel and ground | |
CN103390167A (en) | Multi-characteristic layered traffic sign identification method | |
CN106355180B (en) | A kind of license plate locating method combined based on color with edge feature | |
CN106803070A (en) | A kind of port area Ship Target change detecting method based on remote sensing images | |
CN106250820B (en) | A kind of staircase mouth passenger flow congestion detection method based on image procossing | |
CN109614864B (en) | Method for detecting retractable state of undercarriage of multi-model aircraft at ground-based view angle | |
CN104102909A (en) | Vehicle characteristic positioning and matching method based on multiple-visual information | |
CN104915678A (en) | Detection method and apparatus of target object in power transmission line |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |