CN110047111A - A kind of airplane parking area shelter bridge butting error measurement method based on stereoscopic vision - Google Patents
A kind of airplane parking area shelter bridge butting error measurement method based on stereoscopic vision Download PDFInfo
- Publication number
- CN110047111A CN110047111A CN201910313291.2A CN201910313291A CN110047111A CN 110047111 A CN110047111 A CN 110047111A CN 201910313291 A CN201910313291 A CN 201910313291A CN 110047111 A CN110047111 A CN 110047111A
- Authority
- CN
- China
- Prior art keywords
- parking area
- shelter bridge
- airplane parking
- aircraft door
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
- G06T7/85—Stereo camera calibration
-
- 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
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Closed-Circuit Television Systems (AREA)
- Image Analysis (AREA)
Abstract
A kind of airplane parking area shelter bridge butting error measurement method based on stereoscopic vision.It includes establishing airplane parking area shelter bridge and aircraft door butting error measuring system；Video camera is demarcated, internal and external parameter is obtained；Utilize video camera acquisition airplane parking area shelter bridge and aircraft door docking operation image；To image preprocessing；To characteristic point in acquisition image；Outlier is removed, target feature point is obtained；Solve the 3 d space coordinate of target feature point；Threedimensional model is rebuild according to 3 d space coordinate；By threedimensional model apply to terminal handler to shelter bridge and aircraft hatch docking operation it is real-time assess in and etc..The untouchable of Tilly of the present invention, measurement of full field, precision be high, not vulnerable to the advantages that external world influences, stability is strong; can high-precision, high efficiency, the whole audience non-contactly measure the error that airplane parking area shelter bridge is docked with aircraft door; not only error can accurately be measured, but also shelter bridge realization in airplane parking area can be made to connect with the high-precision of aircraft door.
Description
Technical field
The invention belongs to binocular vision 3 D coordinate measuring technology fields, are stopped more particularly to a kind of based on stereoscopic vision
Machine level ground shelter bridge butting error measurement method.
Background technique
Airplane parking area shelter bridge is also known as connecting bridge (Airport Boarding Bridge), and the passenger important as airport steps on
Equipment of disembarking and the advantage of dependence itself generally use on the major airport in the world, and realization aircraft is docked with terminal, from
And allow and directly step into or leave aircraft when passenger boarding by bridge compartment, it greatly facilitates passenger and passes in and out cabin, it is not only safe but also comfortable.
And under any weather and any temperature, passenger can be allowed to drench with rain when boarding is disembarked from exposing to the weather using shelter bridge.
But when being docked in its working region with aircraft due to airplane parking area shelter bridge, easily occur scratching, positioning docking inaccuracy etc.
Problem causes certain economic loss to airline, therefore guarantee airplane parking area shelter bridge and aircraft to bring inconvenience to passenger
High-precision connection and the problems such as avoiding the occurrence of scratch seem of crucial importance, and then ensure passenger can smooth aboard,
This is also one of important requirement of aviation safety.
From U.S.'s development GPS (GPS) in 1974 and since each application field is succeeded, the world
Major state all the Global Satellite Navigation System of positive development this country (Global Navigation Satellite System,
GNSS).Current main Global Satellite Navigation System has GLONASS (GLONASS) system of the GPS system in the U.S., Russia
The dipper system of system, the Galileo system in Europe and China, and these positioning systems are widely used in Civil Aviation Industry.Inside state
It is the GPS system based on foreign countries that the positioning system that extension set field uses, which imitates the system in external most of airport or use,
Mostly realize that airplane parking area shelter bridge is docked with aircraft using GPS positioning, certainly as the Beidou of China's independent development in recent years is defended
Star navigation system is independently operated Global Satellite Navigation System, and Beidou is applied to Civil Aviation Industry, has huge potentiality and space,
There is biggish meaning for improving civil aviaton, China international influence and technical level.Either Beidou or GPS can expire
The needs of integrity monitoring when foot non-precision approach.In airplane parking area shelter bridge and aircraft docking operation, frequently with GPS positioning side
Method, this method have dead angle in measurement range, interfere vulnerable to extraneous electric wave signal, that is, have that signal accuracy is low, signal is vulnerable to dry
The disadvantages of disturbing.
Summary of the invention
To solve the above-mentioned problems, the airplane parking area shelter bridge docking based on stereoscopic vision that the purpose of the present invention is to provide a kind of
Error measurement method.
In order to achieve the above object, the airplane parking area shelter bridge butting error measurement method provided by the invention based on stereoscopic vision
Including the following steps carried out in order:
Step 1) establishes airplane parking area shelter bridge and aircraft door butting error measuring system；
The system includes two video cameras, synchronous stoboflash control and terminal handler；Wherein: two video cameras
For the image collecting device comprising lighting source and camera, it is respectively placed in airplane parking area shelter bridge front edge of airport pickup port two sides position, and is imaged
Head are to aircraft door；Synchronous stoboflash control is Image Acquisition sync control device, is connected respectively with two video cameras,
For realizing the picture synchronization collection of two video cameras；Terminal handler is connected with two video cameras respectively, passes through two
Video camera acquires the image of airplane parking area shelter bridge and aircraft door docking operation and is handled；
Step 2) marks above-mentioned airplane parking area shelter bridge and two video cameras in aircraft door butting error measuring system
It is fixed, obtain the internal and external parameter of video camera；
Step 3) acquires the image of airplane parking area shelter bridge and aircraft door docking operation using above-mentioned two video camera；
Step 4) pre-processes above-mentioned airplane parking area shelter bridge and the image of aircraft door docking operation, after being corrected
Image；
Step 5) detects the characteristic point in the image after above-mentioned correction, obtains characteristic point；
Step 6) removes outlier from features described above point, obtains target feature point；
Step 7) solves the 3 d space coordinate of above-mentioned target feature point；
Step 8) is docked according to the 3 d space coordinate of above-mentioned target feature point reconstruction airplane parking area shelter bridge with aircraft door
The threedimensional model of process；
Above-mentioned threedimensional model is applied to terminal handler and commented shelter bridge and the real-time of aircraft hatch docking operation by step 9)
In estimating, to instruct the docking operation of airplane parking area shelter bridge and aircraft door.
In step 1), two video cameras use the industrial digital video camera with model.
It is described that above-mentioned airplane parking area shelter bridge and two in aircraft door butting error measuring system are taken the photograph in step 2)
Camera is demarcated, and the method for obtaining the internal and external parameter of video camera is: set the primary optical axis angle of above-mentioned two video camera as
60°；According to binocular stereo vision principle, system calibrating is carried out to two video cameras based on Zhang Zhengyou calibration method, is taken the photograph
Then the initial internal and external parameter of camera is calibrated video camera using the camera intrinsic parameter calibration method of BP neural network,
Obtain the inside and outside parameter of video camera.
It is described to utilize above-mentioned two video camera acquisition airplane parking area shelter bridge and aircraft door docking operation in step 3)
The method of image is:
Under the control of terminal handler, two video camera real-time synchronization acquisitions are controlled using synchronous stoboflash control and are stopped
The two dimensional image of different time points in machine level ground shelter bridge and aircraft door docking operation, and send terminal handler to.
It is described that above-mentioned airplane parking area shelter bridge and the image of aircraft door docking operation are pre-processed in step 4),
The method of image after being corrected is:
Three-dimensional correction is carried out to the distortion parameter in image by epipolar-line constraint first；Then some unrelated letters are filtered out
Breath, wherein the technology including the filtering for applying to image removes dryness, contrast increases and Pseudo Col ored Image, the figure after being corrected
Picture.
In step 5), the characteristic point in the image to after above-mentioned correction is detected, and obtains the side of characteristic point
Method is:
On terminal handler, aircraft door is irised out with rectangle on the image after above-mentioned correction, and by the rectangular area
It is set to target area；Then characteristic point detection is carried out to the image in target area using ORB algorithm, obtains characteristic point, realized
Feature detection；Characteristic point is detected using the FAST algorithm in ORB algorithm, the algorithm be based on characteristic point around pixel ash
Angle value detects the pixel to make a circle in candidate feature point week, if having enough pictures in candidate feature point peripheral region
The gray scale difference value of vegetarian refreshments and the candidate feature point is sufficiently large, then it is assumed that the candidate feature point is a characteristic point；
I (x) is the gray value of any pixel on circumference in above formula, and I (p) is the ash of the candidate feature point p as the center of circle
Angle value, ε d is gray scale difference value threshold value, if gray scale difference value N is greater than gray scale difference value threshold value, then it is assumed that candidate feature point p is a spy
Sign point.
In step 6), described to remove outlier from features described above point, the method for obtaining target feature point is:
(1) central point for above-mentioned all characteristic points is calculated；
(2) distance that each characteristic point arrives central point, and statistical distance distribution are calculated；
(3) then the distance of each characteristic point to central point is compared with threshold value, gets rid of more than threshold by given threshold
Characteristic point, that is, outlier of value, obtains target feature point；
(4) divergence distance in class is calculated, to prove the reliability of target feature point.
In step 7), the method for the 3 d space coordinate of the above-mentioned target feature point of solution is:
Two video cameras and testee are put down using target feature point in two video camera pictures in space formation triangle relation
Imaging point coordinate on face solves the 3 d space coordinate of target feature point.
It is described above-mentioned threedimensional model to be applied into terminal handler shelter bridge was docked with aircraft hatch in step 9)
In the real-time assessment of journey, to instruct the docking operation method of airplane parking area shelter bridge and aircraft door to be:
Terminal handler judges whether the airplane parking area shelter bridge of a direction operation can be with aircraft cabin using above-mentioned threedimensional model
Door collides；If it is judged that the airplane parking area shelter bridge of direction operation will collide with aircraft door, terminal handler
In anti-collision early warning program can issue warning information, to remind the staff of airplane parking area shelter bridge program operation direction again；Such as
Fruit judges that the airplane parking area shelter bridge of direction operation will not collide with aircraft door, then judge whether can be accurately real
Existing airplane parking area shelter bridge is docked with aircraft door, if can not achieve, the staff of airplane parking area shelter bridge can be according to terminal processes
The instruction of device is adjusted, until realizing successfully docking for airplane parking area shelter bridge and aircraft door.
Stereoscopic vision is utilized in airplane parking area shelter bridge butting error measurement method provided by the invention based on stereoscopic vision
The untouchable of (Stereo Vision), measurement of full field, precision be high, not vulnerable to the advantages that external world influences, stability is strong, can
In high precision, high efficiency, the whole audience non-contactly measure the error that airplane parking area shelter bridge is docked with aircraft door, not only can to error into
Row accurately measures, and shelter bridge realization in airplane parking area can be made to connect with the high-precision of aircraft door.Its significance lies in that using
Stereoscopic vision high-precision method not only may be implemented accurately to connect, reduce accident rate, can also realize that monitoring is pre- in time
It is alert, the safety and comfort level of its airplane can be increased for passenger；Wind is not only reduced for airline
It is dangerous, cost has been saved, the satisfaction of user is also improved.
Detailed description of the invention
Fig. 1 is to shut down employed in the airplane parking area shelter bridge butting error measurement method provided by the invention based on stereoscopic vision
Level ground shelter bridge and aircraft door butting error measuring system structure chart.
Fig. 2 is the airplane parking area shelter bridge butting error measuring method flow chart provided by the invention based on stereoscopic vision.
Fig. 3 is binocular camera observation space point schematic diagram in the present invention.
Specific embodiment
The airplane parking area shelter bridge to provided by the invention based on stereoscopic vision, which docks, in the following with reference to the drawings and specific embodiments misses
Difference measurements method is described in detail.
The advantage of comprehensive visual measurement and visual pattern of the present invention, the airplane parking area shelter bridge docking based on stereoscopic vision provided
Error measurement method can make airplane parking area shelter bridge and aircraft door docking operation and have both stability, high-precision detection is known
Not, guarantee is provided for airplane parking area shelter bridge and going on smoothly for aircraft door mating operation, improves airplane parking area shelter bridge operation area
The safety in domain.
As shown in Fig. 2, the airplane parking area shelter bridge butting error measurement method provided by the invention based on stereoscopic vision includes pressing
The following steps that sequence carries out:
Step 1) establishes airplane parking area shelter bridge and aircraft door butting error measuring system as shown in Figure 1；
The system includes two video cameras 1, synchronous stoboflash control 2 and terminal handler 3；Wherein: two are taken the photograph
Camera 1 is the image collecting device comprising lighting source and camera, is respectively placed in airplane parking area shelter bridge front edge of airport pickup port two sides position, and
Camera faces aircraft door；Synchronous stoboflash control 2 is Image Acquisition sync control device, respectively with two video cameras 1
It is connected, for realizing the picture synchronization collection of two video cameras 1；Terminal handler 3 is connected with two video cameras 1 respectively,
It acquires the image of airplane parking area shelter bridge and aircraft door docking operation by two video cameras 1 and is handled；Described two
Video camera 1 is using the industrial digital video camera with model；
Step 2) marks above-mentioned airplane parking area shelter bridge and two video cameras 1 in aircraft door butting error measuring system
It is fixed, obtain the internal and external parameter of video camera 1；
According to binocular stereo vision measurement model, two video cameras 1 and testee spatially need to form triangle relation,
The primary optical axis angle of above-mentioned two video camera 1 is set as 60 °；According to binocular stereo vision principle, using Zhang Zhengyou calibration method as base
Plinth carries out system calibrating to two video cameras 1, obtains the initial internal and external parameter of video camera 1, then using BP neural network
Camera intrinsic parameter calibration method calibrates video camera 1, to further increase the calibration accuracy of video camera 1, reduces subsequent survey
Uncertainty during amount obtains the internal and external parameter of video camera 1.
Video camera 1 can also be used certainly in calibration using calibration manually according to the calibration tool difference used in the present invention
Dynamic calibration, such as the calibration tool case of OpenCV, achievable automatic Calibration.Automatic Calibration journey can also be write in advance in computer
Sequence, to complete the calibration of video camera 1.The present invention is as follows to the calibration sequence of video camera 1: firstly, carrying out to two video cameras 1
Number then carries out stereoscopic vision mark to two video cameras 1 using the Camera Calibration of Stereo Vision System tool in the tool box Matlab
It is fixed.Scaling board is placed in the public area of visual field of two video cameras 1, the different photo of 10 groups of calibration Board positions of shooting, by
The inner parameter of two video cameras 1: focal length, aperture, principal point etc. is obtained after the processing of Matlab tool；External parameter: two camera shootings
Relative distance, angle, rotation of machine 1 etc.；
Step 3) acquires the image of airplane parking area shelter bridge and aircraft door docking operation using above-mentioned two video camera 1；
Under the control of terminal handler 3, two 1 real-time synchronizations of video camera are controlled using synchronous stoboflash control 2 and are adopted
Collect the two dimensional image of different time points in airplane parking area shelter bridge and aircraft door docking operation, and sends terminal handler 3 to；
Step 4) pre-processes above-mentioned airplane parking area shelter bridge and the image of aircraft door docking operation, after being corrected
Image；
Often there is various noise jamming or distortion phenomenon in the image acquired from true environment, therefore after progress
It must be pre-processed before continuous operation.Three-dimensional correction is carried out to the distortion parameter in image by epipolar-line constraint first；So
After filter out some irrelevant informations, emphasize keynote message, improving image quality, prominent characteristics of image；Wherein apply to image
Technology including filtering removes dryness, contrast increases and Pseudo Col ored Image, the image after being corrected；Picture quality it is higher so that
It is more accurate to airplane parking area shelter bridge and the record of aircraft door docking operation；
Step 5) detects the characteristic point in the image after above-mentioned correction, obtains characteristic point；
On terminal handler 3, aircraft door is irised out with rectangle on the image after above-mentioned correction, and by the rectangular area
It is set to target area；Then the image in target area is carried out using ORB (Oriented Brief, towards briefly) algorithm special
Sign point detection, obtains characteristic point, realizes feature detection.Compared to KLT algorithm, SIFT, SURF, Harris etc., ORB algorithm it is comprehensive
Closing performance is best compared with other feature extraction algorithms in various evaluation and tests.ORB algorithm is introduced into characteristic point detection, it can be real
Now to the high-precision of characteristic point, efficient detection in target area；The present invention is using the FAST (features in ORB algorithm
From accelerated segment test) algorithm detects characteristic point, the algorithm be based on characteristic point around pixel
Gray value detects the pixel to make a circle in candidate feature point week, if had in candidate feature point peripheral region enough
The gray scale difference value of pixel and the candidate feature point is sufficiently large, then it is assumed that the candidate feature point is a characteristic point.
I (x) is the gray value of any pixel on circumference in above formula, and I (p) is the ash of the candidate feature point p as the center of circle
Angle value, εdFor gray scale difference value threshold value, if gray scale difference value N is greater than gray scale difference value threshold value, then it is assumed that candidate feature point p is a spy
Sign point.
Step 6) removes outlier from features described above point, obtains target feature point；
Outlier refers to the characteristic point that other characteristic points are deviated significantly from all characteristic points detected.This step uses base
Distance center point is weeded out farther out by the range distribution of statistical nature point to central point in the central point elimination method of distance
The poor characteristic point, that is, outliers of minority, to enhance the robustness of algorithm；Then continue next step if there is no outlier；
The specific method is as follows:
(1) central point for above-mentioned all characteristic points is calculated；
(2) distance that each characteristic point arrives central point, and statistical distance distribution are calculated；
(3) then the distance of each characteristic point to central point is compared with threshold value, gets rid of more than threshold by given threshold
Characteristic point, that is, outlier of value, obtains target feature point.
(4) divergence distance in class is calculated, it was demonstrated that the reliability of target feature point.
Step 7) solves the 3 d space coordinate of above-mentioned target feature point；
Binocular stereo vision imitates mankind's eyes and obtains three-dimensional information, is made of two video cameras 1, as shown in Figure 3.Two
Video camera 1 and testee are in space formation triangle relation, using target feature point in two video cameras 1 as the imaging in plane
Point coordinate can solve the 3 d space coordinate of target feature point.
Wherein, OLXLYLZLFor the coordinate system of left side camera 1, photo coordinate system olxlyl, optical axis direction ZL；Together
Reason, ORXRYRZRFor the coordinate system of right camera 1, photo coordinate system oRxRyR, optical axis direction ZR；PL, PRRespectively mesh
Characteristic point is marked in left side, right camera 1 as the imaging point coordinate in plane, the intersection point P of two rays in figureWAs target is special
Sign point is in world coordinate system XWYWZWUnder coordinate.
In conjunction with Fig. 3, the positional relationship expression formula between two video cameras 1 can be obtained are as follows:
Wherein,Spin moment of expression 1 coordinate system of right camera to 1 coordinate system of left side camera
Battle array；T=(t1 t2 t3)T, the translation matrix of expression 1 coordinate system of right camera to 1 coordinate system of left side camera.
According to video camera Perspective transformation model, the target feature point indicated under sensor coordinate system and two video cameras 1
As the correspondent transform relationship between the imaging point in plane is:
So can be in the hope of the 3 d space coordinate of target feature point:
Step 8) is docked according to the 3 d space coordinate of above-mentioned target feature point reconstruction airplane parking area shelter bridge with aircraft door
The threedimensional model of process；
Above-mentioned threedimensional model is applied to terminal handler 3 and commented shelter bridge and the real-time of aircraft hatch docking operation by step 9)
In estimating, to instruct the docking operation of airplane parking area shelter bridge and aircraft door；
Terminal handler 3 judges whether the airplane parking area shelter bridge of a direction operation can be with aircraft cabin using above-mentioned threedimensional model
Door collides；If it is judged that the airplane parking area shelter bridge of direction operation will collide with aircraft door, terminal handler 3
In anti-collision early warning program can issue warning information, to remind the staff of airplane parking area shelter bridge program operation direction again；Such as
Fruit judges that the airplane parking area shelter bridge of direction operation will not collide with aircraft door, then judge whether can be accurately real
Existing airplane parking area shelter bridge is docked with aircraft door, if can not achieve, the staff of airplane parking area shelter bridge can be according to terminal processes
The instruction of device 3 is adjusted, until realizing successfully docking for airplane parking area shelter bridge and aircraft door.
A specific embodiment of the invention is described in conjunction with attached drawing above, but these explanations cannot be understood to limit
The scope of the present invention, protection scope of the present invention are limited by appended claims, any in the claims in the present invention base
Change on plinth is all protection scope of the present invention.
Claims (9)
1. a kind of airplane parking area shelter bridge butting error measurement method based on stereoscopic vision, it is characterised in that: described based on solid
The airplane parking area shelter bridge butting error measurement method of vision includes the following steps carried out in order:
Step 1) establishes airplane parking area shelter bridge and aircraft door butting error measuring system；
The system includes two video cameras (1), synchronous stoboflash control (2) and terminal handler (3)；Wherein: two
Video camera (1) is the image collecting device comprising lighting source and camera, is respectively placed in airplane parking area shelter bridge front edge of airport pickup port both sides
Position, and camera faces aircraft door；Synchronous stoboflash control (2) are Image Acquisition sync control device, respectively with two
Video camera (1) is connected, for realizing the picture synchronization collection of two video cameras (1)；Terminal handler (3) is taken the photograph with two respectively
Camera (1) is connected, and image and the progress of airplane parking area shelter bridge and aircraft door docking operation are acquired by two video cameras (1)
Processing；
Step 2) marks above-mentioned airplane parking area shelter bridge and two video cameras (1) in aircraft door butting error measuring system
It is fixed, obtain the internal and external parameter of video camera (1)；
Step 3) acquires the image of airplane parking area shelter bridge and aircraft door docking operation using above-mentioned two video camera (1)；
Step 4) pre-processes above-mentioned airplane parking area shelter bridge and the image of aircraft door docking operation, the figure after being corrected
Picture；
Step 5) detects the characteristic point in the image after above-mentioned correction, obtains characteristic point；
Step 6) removes outlier from features described above point, obtains target feature point；
Step 7) solves the 3 d space coordinate of above-mentioned target feature point；
Step 8) rebuilds airplane parking area shelter bridge and aircraft door docking operation according to the 3 d space coordinate of above-mentioned target feature point
Threedimensional model；
Above-mentioned threedimensional model is applied to real-time assessment of the terminal handler (3) to shelter bridge and aircraft hatch docking operation by step 9)
In, to instruct the docking operation of airplane parking area shelter bridge and aircraft door.
2. the airplane parking area shelter bridge butting error measurement method according to claim 1 based on stereoscopic vision, it is characterised in that:
In step 1), two video cameras (1) are using the industrial digital video camera with model.
3. the airplane parking area shelter bridge butting error measurement method according to claim 1 based on stereoscopic vision, it is characterised in that:
In step 2), two video cameras (1) in above-mentioned airplane parking area shelter bridge and aircraft door butting error measuring system
It is demarcated, the method for obtaining the internal and external parameter of video camera (1) is: setting the primary optical axis angle of above-mentioned two video camera (1)
It is 60 °；According to binocular stereo vision principle, system calibrating is carried out to two video cameras 1 based on Zhang Zhengyou calibration method, is obtained
The initial internal and external parameter of video camera (1), then using BP neural network camera intrinsic parameter calibration method to video camera (1) into
Row calibration, obtains the inside and outside parameter of video camera (1).
4. the airplane parking area shelter bridge butting error measurement method according to claim 1 based on stereoscopic vision, it is characterised in that:
In step 3), the image using above-mentioned two video camera (1) acquisition airplane parking area shelter bridge and aircraft door docking operation
Method be:
Under the control of terminal handler (3), two video camera (1) real-time synchronizations are controlled using synchronous stoboflash control (2)
The two dimensional image of different time points in airplane parking area shelter bridge and aircraft door docking operation is acquired, and sends terminal handler (3) to.
5. the airplane parking area shelter bridge butting error measurement method according to claim 1 based on stereoscopic vision, it is characterised in that:
It is described that above-mentioned airplane parking area shelter bridge and the image of aircraft door docking operation are pre-processed in step 4), it is corrected
The method of image afterwards is:
Three-dimensional correction is carried out to the distortion parameter in image by epipolar-line constraint first；Then some irrelevant informations are filtered out,
In apply to image filtering remove dryness, contrast increase and Pseudo Col ored Image including technology, the image after being corrected.
6. the airplane parking area shelter bridge butting error measurement method according to claim 1 based on stereoscopic vision, it is characterised in that:
In step 5), the characteristic point in the image to after above-mentioned correction is detected, and the method for obtaining characteristic point is:
On terminal handler (3), aircraft door is irised out with rectangle on the image after above-mentioned correction, and the rectangular area is determined
For target area；Then characteristic point detection is carried out to the image in target area using ORB algorithm, obtains characteristic point, realized special
Sign detection；Characteristic point is detected using the FAST algorithm in ORB algorithm, the algorithm be based on characteristic point around pixel gray level
Value detects the pixel to make a circle in candidate feature point week, if having enough pixels in candidate feature point peripheral region
Point is sufficiently large with the gray scale difference value of the candidate feature point, then it is assumed that the candidate feature point is a characteristic point；
I (x) is the gray value of any pixel on circumference in above formula, and I (p) is the gray value of the candidate feature point as the center of circle, εd
For gray scale difference value threshold value, if gray scale difference value N is greater than gray scale difference value threshold value, then it is assumed that pixel p is a characteristic point.
7. the airplane parking area shelter bridge butting error measurement method according to claim 1 based on stereoscopic vision, it is characterised in that:
In step 6), described to remove outlier from features described above point, the method for obtaining target feature point is:
(1) central point for above-mentioned all characteristic points is calculated；
(2) distance that each characteristic point arrives central point, and statistical distance distribution are calculated；
(3) then the distance of each characteristic point to central point is compared with threshold value, gets rid of more than threshold value by given threshold
Characteristic point, that is, outlier, obtains target feature point；
(4) divergence distance in class is calculated, to prove the reliability of target feature point.
8. the airplane parking area shelter bridge butting error measurement method according to claim 1 based on stereoscopic vision, it is characterised in that:
In step 7), the method for the 3 d space coordinate of the above-mentioned target feature point of solution is:
Two video cameras (1) and testee are in space formation triangle relation, using target feature point in two video cameras 1 as flat
Imaging point coordinate on face solves the 3 d space coordinate of target feature point.
9. the airplane parking area shelter bridge butting error measurement method according to claim 1 based on stereoscopic vision, it is characterised in that:
It is described that above-mentioned threedimensional model is applied into terminal handler to the real-time of shelter bridge and aircraft hatch docking operation in step 9)
In assessment, to instruct the docking operation method of airplane parking area shelter bridge and aircraft door to be:
Terminal handler (3) judges whether the airplane parking area shelter bridge of a direction operation can be with aircraft door using above-mentioned threedimensional model
It collides；If it is judged that the airplane parking area shelter bridge of direction operation will collide with aircraft door, terminal handler (3)
In anti-collision early warning program can issue warning information, to remind the staff of airplane parking area shelter bridge program operation direction again；Such as
Fruit judges that the airplane parking area shelter bridge of direction operation will not collide with aircraft door, then judge whether can be accurately real
Existing airplane parking area shelter bridge is docked with aircraft door, if can not achieve, the staff of airplane parking area shelter bridge can be according to terminal processes
The instruction of device (3) is adjusted, until realizing successfully docking for airplane parking area shelter bridge and aircraft door.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910313291.2A CN110047111B (en) | 2019-04-18 | 2019-04-18 | Parking apron corridor bridge butt joint error measuring method based on stereoscopic vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910313291.2A CN110047111B (en) | 2019-04-18 | 2019-04-18 | Parking apron corridor bridge butt joint error measuring method based on stereoscopic vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110047111A true CN110047111A (en) | 2019-07-23 |
| CN110047111B CN110047111B (en) | 2022-12-27 |
Family
ID=67277834
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910313291.2A Active CN110047111B (en) | 2019-04-18 | 2019-04-18 | Parking apron corridor bridge butt joint error measuring method based on stereoscopic vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110047111B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110641721A (en) * | 2019-10-16 | 2020-01-03 | 北京天睿空间科技股份有限公司 | Boarding bridge parking method |
| CN110750101A (en) * | 2019-10-16 | 2020-02-04 | 北京天睿空间科技股份有限公司 | Boarding bridge parking position setting method oriented to automatic operation |
| CN111598950A (en) * | 2020-04-23 | 2020-08-28 | 四川省客车制造有限责任公司 | Automatic passenger train hinging method and system based on machine vision |
| CN112528729A (en) * | 2020-10-19 | 2021-03-19 | 浙江大华技术股份有限公司 | Video-based airplane bridge approach event detection method and device |
| CN114559131A (en) * | 2020-11-27 | 2022-05-31 | 北京颖捷科技有限公司 | Welding control method and device and upper computer |
| CN114708422A (en) * | 2022-02-14 | 2022-07-05 | 清华大学 | Binocular image-based cabin door coordinate calculation method and device |
| CN118092478A (en) * | 2024-04-28 | 2024-05-28 | 浙江省圣翔协同创新发展研究院 | Method and system for controlling return voyage based on mobile parking apron |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2373669A1 (en) * | 2002-02-27 | 2003-08-27 | Indal Technologies Inc. | Imaging system for a passenger bridge of the like for docking automatically with an aircraft |
| CN103419944A (en) * | 2012-05-25 | 2013-12-04 | 深圳中集天达空港设备有限公司 | Air bridge and automatic abutting method therefor |
| CN105487092A (en) * | 2014-12-30 | 2016-04-13 | 大连现代高技术集团有限公司 | Navigation system for airport lounge bridge docking airplane hatch |
| CN105812733A (en) * | 2016-03-15 | 2016-07-27 | 中国民用航空总局第二研究所 | Civil aviation air traffic control scene monitoring and guiding system |
| CN106448275A (en) * | 2014-12-30 | 2017-02-22 | 大连现代高技术集团有限公司 | Visualization-based airplane berth real-time guiding system |
-
2019
- 2019-04-18 CN CN201910313291.2A patent/CN110047111B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2373669A1 (en) * | 2002-02-27 | 2003-08-27 | Indal Technologies Inc. | Imaging system for a passenger bridge of the like for docking automatically with an aircraft |
| CN103419944A (en) * | 2012-05-25 | 2013-12-04 | 深圳中集天达空港设备有限公司 | Air bridge and automatic abutting method therefor |
| CN105487092A (en) * | 2014-12-30 | 2016-04-13 | 大连现代高技术集团有限公司 | Navigation system for airport lounge bridge docking airplane hatch |
| CN106448275A (en) * | 2014-12-30 | 2017-02-22 | 大连现代高技术集团有限公司 | Visualization-based airplane berth real-time guiding system |
| CN105812733A (en) * | 2016-03-15 | 2016-07-27 | 中国民用航空总局第二研究所 | Civil aviation air traffic control scene monitoring and guiding system |
Non-Patent Citations (1)
| Title |
|---|
| 费春国等: "机场廊桥设备监测系统的设计与应用", 《测控技术》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110641721A (en) * | 2019-10-16 | 2020-01-03 | 北京天睿空间科技股份有限公司 | Boarding bridge parking method |
| CN110750101A (en) * | 2019-10-16 | 2020-02-04 | 北京天睿空间科技股份有限公司 | Boarding bridge parking position setting method oriented to automatic operation |
| CN111598950A (en) * | 2020-04-23 | 2020-08-28 | 四川省客车制造有限责任公司 | Automatic passenger train hinging method and system based on machine vision |
| CN112528729A (en) * | 2020-10-19 | 2021-03-19 | 浙江大华技术股份有限公司 | Video-based airplane bridge approach event detection method and device |
| CN114559131A (en) * | 2020-11-27 | 2022-05-31 | 北京颖捷科技有限公司 | Welding control method and device and upper computer |
| CN114708422A (en) * | 2022-02-14 | 2022-07-05 | 清华大学 | Binocular image-based cabin door coordinate calculation method and device |
| CN118092478A (en) * | 2024-04-28 | 2024-05-28 | 浙江省圣翔协同创新发展研究院 | Method and system for controlling return voyage based on mobile parking apron |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110047111B (en) | 2022-12-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110047111A (en) | A kind of airplane parking area shelter bridge butting error measurement method based on stereoscopic vision | |
| WO2022061945A1 (en) | Power line safe distance measurement method | |
| JP6484729B2 (en) | Unmanned aircraft depth image acquisition method, acquisition device, and unmanned aircraft | |
| CN107917695B (en) | House inclination monitoring method based on image recognition technology | |
| CN105841688B (en) | A kind of ship auxiliary anchors alongside the shore method and system | |
| CN108986070B (en) | Rock crack propagation experiment monitoring method based on high-speed video measurement | |
| US10909395B2 (en) | Object detection apparatus | |
| CN106978774B (en) | A kind of road surface pit slot automatic testing method | |
| CN106403900B (en) | Flying object tracking location system and method | |
| CN107560592B (en) | Precise distance measurement method for photoelectric tracker linkage target | |
| CN111435081B (en) | Sea surface measuring system, sea surface measuring method and storage medium | |
| CN109269525B (en) | Optical measurement system and method for take-off or landing process of space probe | |
| CN113359097A (en) | Millimeter wave radar and camera combined calibration method | |
| CN105953741B (en) | System and method for measuring local geometric deformation of steel structure | |
| CN110470226A (en) | A kind of bridge structure displacement measurement method based on UAV system | |
| CN103852060A (en) | Visible light image distance measuring method based on monocular vision | |
| CN106971408A (en) | A kind of camera marking method based on space-time conversion thought | |
| CN107271445B (en) | Defect detection method and device | |
| CN109341668A (en) | Polyphaser measurement method based on refraction projection model and beam ray tracing method | |
| CN111707668A (en) | Tunnel detection and image processing method based on sequence image | |
| CN109919856A (en) | Bituminous pavement construction depth detection method based on binocular vision | |
| Crispel et al. | All-sky photogrammetry techniques to georeference a cloud field | |
| CN110044266B (en) | Photogrammetry system based on speckle projection | |
| CN113739720A (en) | Underwater high-precision measurement and defect detection method integrating acoustic method and optical method | |
| CN106447729A (en) | 2 dimensional digital image related compensation method based on transformation of coordinates and 2 dimensional optical digital image related extensometer |
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 |