CN108263283A - More marshalling varied angle vehicle panoramic viewing system calibration and joining method - Google Patents
More marshalling varied angle vehicle panoramic viewing system calibration and joining method Download PDFInfo
- Publication number
- CN108263283A CN108263283A CN201810074955.XA CN201810074955A CN108263283A CN 108263283 A CN108263283 A CN 108263283A CN 201810074955 A CN201810074955 A CN 201810074955A CN 108263283 A CN108263283 A CN 108263283A
- Authority
- CN
- China
- Prior art keywords
- compartment
- birds
- eye view
- eye
- camera
- 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
- 238000000034 method Methods 0.000 title claims description 28
- 238000005304 joining Methods 0.000 title description 4
- 238000013480 data collection Methods 0.000 claims abstract description 20
- 238000012937 correction Methods 0.000 claims description 31
- 230000004927 fusion Effects 0.000 claims description 24
- 238000001514 detection method Methods 0.000 claims description 21
- 238000013507 mapping Methods 0.000 claims description 21
- 241000251468 Actinopterygii Species 0.000 claims description 14
- 238000013519 translation Methods 0.000 claims description 11
- 239000004744 fabric Substances 0.000 claims description 10
- 201000003373 familial cold autoinflammatory syndrome 3 Diseases 0.000 claims description 8
- 230000000007 visual effect Effects 0.000 claims description 8
- 238000005520 cutting process Methods 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims description 6
- 230000003068 static effect Effects 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 5
- 238000005286 illumination Methods 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 235000004522 Pentaglottis sempervirens Nutrition 0.000 claims description 2
- 238000012545 processing Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000007500 overflow downdraw method Methods 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005684 electric field Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R1/00—Optical viewing arrangements; Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles
-
- G06T3/047—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
- G06T3/4038—Scaling the whole image or part thereof for image mosaicing, i.e. plane images composed of plane sub-images
-
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
- B60R2300/10—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of camera system used
- B60R2300/105—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of camera system used using multiple cameras
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
- B60R2300/30—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of image processing
- B60R2300/303—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of image processing using joined images, e.g. multiple camera images
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
- B60R2300/60—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by monitoring and displaying vehicle exterior scenes from a transformed perspective
- B60R2300/607—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by monitoring and displaying vehicle exterior scenes from a transformed perspective from a bird's eye viewpoint
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
- B60R2300/80—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the intended use of the viewing arrangement
- B60R2300/806—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the intended use of the viewing arrangement for aiding parking
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Abstract
The present invention provides a kind of for organizing into groups the panoramic looking-around parking assisting system of varied angle vehicle, including fish-eye camera, hinged disk angle sensing equipment and data collection processor more, it is characterised in that:The video pictures and the angle information of hinged disk angle sensing equipment acquisition that panoramic looking-around parking assisting system is acquired using the fish-eye camera for being at least 180 degree mounted on two often saved on vehicle car or three orientation field angles are handled to obtain the seamless spliced panoramic looking-around image in more marshalling varied angle vehicle perimeter regions through data collection processor;Hinged disk angle sensing equipment is used to measure its two hinged angled information of section compartment institute in real time, while handling measured angle real-time delivery into data collection processor between compartment.The present invention is by acquiring, parsing vehicle hinged disk splice angle, and when in compartment, relative rotation is that camera position changes relatively, real time modifying panoramic mosaic parameter is realized and organizes into groups real-time seamless panoramas splicing more.
Description
Technical field
The invention belongs to vehicle safety auxiliary and vehicle electric fields, and in particular to one kind is for mostly marshalling varied angle vehicle
The calibration of panoramic looking-around system and joining method.
Background technology
As car ownership increases rapidly, traffic safety is increasingly becoming a great social concern.Panorama ring
Viewing system can effectively assist driver, reduce vehicle in the accident rate run at a low speed.At present, in the market complete
Scape looks around parking assisting system, and the overwhelming majority is for riding car, using four cameras, before being arranged in automobile
Below bumper Logo, below left and right rearview mirror, at rear license plate lamp;Minority is directed to the panorama system of commercial car, four cameras
It is attached separately to the point midway of vehicle roof four direction.Either passenger car or commercial car panoramic looking-around system, run over
Camera relative position immobilizes in journey.
More marshalling varied angle vehicles have more piece compartment, installation are needed more than 4 cameras, to realize panoramic mosaic;It is compile more
Group varied angle automobile body is larger, and the variation of each camera the image collected object of which movement and light is different, it is desirable that more preferable
White balance algorithm realize image co-registration;The angled real-time change of institute between each compartment in the process of moving of more marshalling varied angle vehicles
Change, lead to relative position between the camera installed on different compartments also real-time change.So using existing panoramic looking-around
Scheme can not realize the seamless spliced panoramic looking-around requirement of more marshalling varied angle vehicles.
Invention content
The technical problem to be solved by the present invention is to:A kind of seamless spliced panorama ring for mostly marshalling varied angle vehicle is provided
Viewing system is demarcated and joining method, for such vehicle traveling and park auxiliary tool be provided.
The technical solution taken by the invention to solve the above technical problem is used to organize into groups varied angle vehicles more to be a kind of
Panoramic looking-around parking assisting system, including fish-eye camera, hinged disk angle sensing equipment and data collection processor, feature
It is:
Panoramic looking-around parking assisting system utilize be mounted on often save vehicle car on two or three orientation field angles extremely
The angle information for the video pictures of the fish-eye camera of 180 degree acquisition and the acquisition of hinged disk angle sensing equipment is adopted through data less
Set processor is handled to obtain the seamless spliced panoramic looking-around image in more marshalling varied angle vehicle perimeter regions;
Hinged disk angle sensing equipment is used to measure its two hinged angled information of section compartment institute in real time between compartment, adopts
It is connect with bus mode with the data collection processor, measured angle real-time delivery is carried out to data collection processor
Processing.
Further, data collection processor includes fish eye images distortion correction unit, Corner Detection unit, perspective transform
Unit, bicycle compartment image mosaic unit, bicycle compartment image fusion unit, hinged disk angle acquisition unit, more compartment image mosaics
Unit, more compartment image fusion units;Wherein:
Fish eye images distortion correction unit is used for the internal structure according to each fish-eye camera and the distortion model of foundation, mark
Surely camera parameter and distortion correction parameter are obtained, obtains the mapping relations from fish eye images to distortion correction image;
In the image that Corner Detection unit is captured in each fish-eye camera, detection calibration cloth angle point;Perspective transform list
The practical corner location that the preferable corner location and detection that member is obtained according to measurement scene obtain will come from different flakes and image
The image of head, projects under the same coordinate system and becomes birds-eye view, establish by the mapping relations of correction figure to birds-eye view;
Bicycle compartment image mosaic unit, for in the birds-eye view that adjacent camera is converted to overlapping region into
All camera birds-eye views in bicycle compartment are spliced into bicycle compartment panorama birds-eye view, it is complete to ultimately produce bicycle compartment by row Feature Points Matching
Scape birds-eye view and the mapping relations of each camera flake distortion figure, generate and preserve look-up table;
Bicycle compartment image fusion unit for the adjacent camera image seam crossing in panorama birds-eye view, delimit transition region
Splicing seams using the method for Weighted Fusion, are eliminated in domain;
Hinged disk angle acquisition unit is connect by bus with hinged disk angle sensing equipment, receives and parses through phase between compartment
To angle information;
The independent birds-eye view in each compartment on the basis of hinge joint, is cut and is spliced by more compartment image mosaic units, root
The independent birds-eye view in corresponding compartment is rotated according to hinged disk angle information, while upper and lower translation is carried out to global birds-eye view,
To adapt to screen display demand;
More compartment image fusion units carry out each camera global white balance, to the independent compartment bird after each cutting
Look down from a height each edge of figure is weighted fusion, to eliminate the splicing seams of more compartment birds-eye views splicings.
The invention additionally provides a kind of method that more marshalling varied angle vehicle panoramic viewing systems are demarcated and spliced,
It is characterized in that, specifically includes following steps:
S1, fish eye images distortion correction unit are used for according to the internal structure of each fish-eye camera and the distortion mould of foundation
Type, calibration obtain camera parameter and distortion correction parameter, obtain the mapping relations from fish eye images to distortion correction image;
In S2, the image captured in each fish-eye camera, detection calibration cloth angle point;
S3, the practical corner location detected according to S2 with reference to the preferable corner location that measurement scene obtains, will come from
The image of different fish-eye cameras projects under the same coordinate system and becomes birds-eye view, establishes by the mapping of correction figure to birds-eye view
Relationship;
S4, bicycle compartment image mosaic unit in the birds-eye view that adjacent camera is converted to overlapping region carry out
All camera birds-eye views in bicycle compartment are spliced into bicycle compartment panorama birds-eye view, ultimately produce bicycle compartment by Feature Points Matching for the first time
Panorama birds-eye view and the mapping relations of each camera flake distortion figure, form of look preserve in the memory unit;
S5, after obtaining look-up table, the original of fish-eye camera acquisition is obtained from storage unit by reading lookup table mode
The mapping relation information of video pictures pixel and bicycle compartment panorama birds-eye view pixel, regards what all fish-eye cameras acquired
Frequency picture is mapped to bicycle compartment panorama birds-eye view in real time;
S6, the adjacent camera image seam crossing in panorama birds-eye view delimit transitional region, using the side of Weighted Fusion
Method eliminates splicing seams;
S7, the independent birds-eye view in each compartment on the basis of hinge joint is cut, is then spliced into static more compartment panoramas
Birds-eye view.
S8, hinged disk angle sensing equipment information being received by bus, parsing obtains relative angle information between compartment, according to
Hinged disk angle information rotates the independent birds-eye view in corresponding compartment, while carries out upper and lower translation to global birds-eye view, with
Adapt to screen display demand;
S9, global white balance is carried out to the image that all cameras capture, eliminates illumination effect;After each cutting
Each edge of independent compartment birds-eye view be weighted fusion, to eliminate the splicing seams of more compartment birds-eye views splicings.
Further, the S1 is used as camera distortion model using multinomial model, and chessboard is included using single width
The fish eye images of lattice complete camera calibration.
Further, the S2 is detected first in the gridiron pattern array calibrating cloth of fish-eye camera central region
Angle point, it is emerging feeling then according to part corner location delimitation for the area-of-interest for detecting visual field both sides black block plaid
Quadrangle fitting is carried out in interesting region, by limiting quadrangle position, quadrangle area, quadrangle form, adjacent side ratio, right
Linea angulata obtains black block plaid profile and four apex coordinates, makes around apex coordinate than exclusive PCR quadrangular configuration
With sub-pix angular-point detection method, black block plaid vertex position is determined.
Further, in the S7, front compartment, trunk birds-eye view are not cut out, and middle compartment birds-eye view is with wide in vehicle body
Degree direction is not cut out, allow in front compartment birds-eye view in middle compartment birds-eye view before-middle compartment hinge joint position overlaps, allow rear car
It is overlapped in the birds-eye view of compartment with rear-middle compartment hinge joint position in middle compartment birds-eye view, is spliced into static more compartment panoramas and gets a bird's eye view
Figure.
Further, in the S8, compartment birds-eye view without rotation, front compartment according to before-middle hinged disk angle information
Rotated around preceding-middle hinge joint, trunk according to after-middle hinged disk angle information rotates around rear-middle hinge joint;Current compartment or after
When compartment exceeds indication range, panoramic mosaic figure is integrally translated in the opposite direction to turn, middle compartment exceeds after translation
During indication range, panoramic mosaic image is integrally shunk.
Beneficial effects of the present invention are:
1st, current existing panoramic looking-around system, be for the constant situation of camera relative position, calibration for the first time,
After the completion of splicing, panoramic mosaic is realized with preset parameter.In mostly marshalling varied angle Ackermann steer angle, the camera position in different compartments
Opposite variation is put, panoramic mosaic is carried out according to preset parameter, serious figure can be generated in the stitching portion of different compartment birds-eye views
As the changing of the relative positions, splicing can not be realized.The present invention is relatively rotated in compartment and is imaged by acquiring, parsing vehicle hinged disk splice angle
When head position changes relatively, real time modifying panoramic mosaic parameter realizes the real-time seamless panorama splicing of more marshallings.
2nd, current existing panoramic looking-around system, carries out panoramic mosaic using 4 cameras mostly, and only a few uses 6
Camera carries out panoramic mosaic, is not spliced using 8 or more cameras.But mostly three compartment of marshalling vehicle needs 8
Camera could complete panoramic mosaic.The present invention solves currently embedded formula using the direct-connected transmission method of CVBS vision signals
Not the problem of transmission bandwidth does not support 8 road cameras to input simultaneously in scheme;Bicycle compartment panoramic mosaic is carried out using LUT Method,
It realizes that more compartments splice by rotating bicycle compartment panorama birds-eye view, reduces operand, ensure real-time.
3rd, when carrying out more marshalling panorama birds-eye view displays, if middle compartment and its birds-eye view are placed in display screen
When the heart, current compartment or larger trunk relative angle, front compartment or trunk can part beyond screen display range, headstock or
Environmental information around the tailstock will be unable to be shown in display screen.The present invention will organize into groups birds-eye view more when the above situation occurs
It is whole to be moved to turning to opposite direction;After moving a certain distance, when middle compartment will also deflect away from display area, it will compile more
Group birds-eye view overall shrinkage, so as to ensure that vehicle perimeter panoramic information is remained in indication range.
Description of the drawings
Fig. 1 is system layout.
Fig. 2 is panorama mosaic method flow chart.
Fig. 3 is bicycle compartment panoramic mosaic method detailed.
Fig. 4 is more compartment panoramic mosaic method detaileds.
Fig. 5 is bicycle compartment splicing seams schematic diagram.
Fig. 6 is more compartment splicing seams schematic diagrames.
Specific embodiment
In order to allow the technical staff of this field panoramic looking-around parking assisting system that can be better understood from the technology of the present invention
Scheme, below in conjunction with the accompanying drawings 1-6 make further details of elaboration to the present invention.
This embodiment offers a kind of for organizing into groups the panoramic looking-around parking assisting system of varied angle vehicle, including flake more
Camera, hinged disk angle sensing equipment and data collection processor, wherein, panoramic looking-around parking assisting system is utilized and is mounted on
It often saves two on compartment or three orientation field angles is at least video pictures and hinged disk that the fish-eye camera of 180 degree acquires
The angle information of angle sensing equipment acquisition is handled to obtain more marshalling varied angle vehicle perimeter areas through data collection processor
The seamless spliced panoramic looking-around image in domain.
Hinged disk angle sensing equipment is used to measure its two hinged angled information of section compartment institute in real time between compartment, adopts
It is connect with bus mode with the data collection processor, measured angle real-time delivery is carried out to data collection processor
Processing.
Data collection processor includes fish eye images distortion correction unit, Corner Detection unit, perspective transform unit, bicycle
Compartment image mosaic unit, bicycle compartment image fusion unit, hinged disk angle acquisition unit, more compartment image mosaic units, more vehicles
Compartment image fusion unit;Wherein:
Fish eye images distortion correction unit is used for the internal structure according to each fish-eye camera and the distortion model of foundation, mark
Surely camera parameter and distortion correction parameter are obtained, obtains the mapping relations from fish eye images to distortion correction image;
In the image that Corner Detection unit is captured in each fish-eye camera, detection calibration cloth angle point;Perspective transform list
The practical corner location that the preferable corner location and detection that member is obtained according to measurement scene obtain will come from different flakes and image
The image of head, projects under the same coordinate system and becomes birds-eye view, establish by the mapping relations of correction figure to birds-eye view;
Bicycle compartment image mosaic unit, for in the birds-eye view that adjacent camera is converted to overlapping region into
All camera birds-eye views in bicycle compartment are spliced into bicycle compartment panorama birds-eye view, it is complete to ultimately produce bicycle compartment by row Feature Points Matching
Scape birds-eye view and the mapping relations of each camera flake distortion figure, generate and preserve look-up table;
Bicycle compartment image fusion unit for the adjacent camera image seam crossing in panorama birds-eye view, delimit transition region
Splicing seams using the method for Weighted Fusion, are eliminated in domain;
Hinged disk angle acquisition unit is connect by bus with hinged disk angle sensing equipment, receives and parses through phase between compartment
To angle information;
The independent birds-eye view in each compartment on the basis of hinge joint, is cut and is spliced by more compartment image mosaic units, root
The independent birds-eye view in corresponding compartment is rotated according to hinged disk angle information, while upper and lower translation is carried out to global birds-eye view,
To adapt to screen display demand;
More compartment image fusion units carry out each camera global white balance, to the independent compartment bird after each cutting
Look down from a height each edge of figure is weighted fusion, to eliminate the splicing seams of more compartment birds-eye views splicings.
As shown in the figure, parking the present embodiment provides a kind of panoramic looking-around for being used for three sections marshalling varied angle vehicle assists system
System, it using three section marshalling varied angle vehicles on installation 8 orientation field angles be at least 180 degree fish-eye camera acquisition
Video pictures are handled to obtain the seamless spliced panorama ring in more marshalling varied angle vehicle perimeter regions through data collection processor
Visible image;Wherein described camera arrangement is:For three section marshalling varied angle vehicles, in front compartment and trunk
On, 3 cameras are respectively arranged, front compartment is located at the point midway on compartment roof front side, left side, right side, rear compartment position
In compartment roof rear side, left side, right side point midway;On middle compartment, 2 cameras are arranged, positioned at a compartment roof left side
Side and right side point midway.
Hinged disk angle sensing equipment is between the compartment:Its two hinged angled letter of section compartment institute is measured in real time
Breath, is connect using bus mode with the data collection processor, by measured angle real-time delivery data collection processor
It is handled.
By taking three section compartment vehicles as an example, there are two hinged disk angle sensing equipment, before measuring respectively, the relative angle in middle compartment
Degree and in, the relative angle of trunk.
In the present embodiment, more compartment image fusion units, front compartment, trunk birds-eye view are not cut out, intermediate vehicle
Compartment birds-eye view is cut out to front and rear hinged disk in length of wagon direction not cut out in vehicle-body width direction and extends to the outside a little place;
Middle compartment is rotated without rotation, front compartment according to preceding hinged disk angle information around preceding hinge joint, and trunk is hinged according to after
Disk angle information is rotated around rear hinge joint;The splicing line of three compartment birds-eye views is the edge of middle compartment birds-eye view:To three compartments
The method that the edge of birds-eye view uses Weighted Fusion, realizes fade effect, reaches the mesh eliminated splicing line and seamlessly transitted
's;When rotation angle is larger, and front compartment or trunk exceed indication range, by the whole side opposite to steering of panoramic mosaic figure
To translation, when middle compartment exceeds indication range after translation, panoramic mosaic image is integrally shunk.
Data collection processor in this example is made of a main embedded system and three sub- embedded system collaborations,
Three sub- embedded systems respectively handle the image data in a compartment, while are transferred data to by CVBS signal transmission forms
In main embedded system, main embedded system integrates every terms of information, completes Panorama Mosaic.
The embodiment, which additionally provides, a kind of demarcated and is spelled using above-mentioned more marshalling varied angle vehicle panoramic viewing systems
The method connect, includes the following steps:
S1, fish eye images distortion correction unit are used for according to the internal structure of each fish-eye camera and the distortion mould of foundation
Type, calibration obtain camera parameter and distortion correction parameter, obtain the mapping relations from fish eye images to distortion correction image.
The present embodiment uses polynomial distortion model, between the ideograph and original distortion figure after model description correction
Pixel point correspondence.
Postulated point (xu,yu) be after correction in ideograph a bit, (xd,yd) be in original distortion figure a bit, the two it
Between nonlinear correspondence relation, can be represented with following formula:
xu=(xd-Cx)F(Λ)+Cx
yu=(yd-Cy)F(Λ)+Cy
Wherein Λ=[λ1,λ2,...,λL] it is distortion factor, Cx,CyIt is center of distortion, L generally takes 2-4.The form of F is such as
Under.
Wherein γ is catercorner length.
In practical applications, the uncalibrated image of an X-comers is shot with fish-eye camera to be calibrated first, makes chess
Disk lattice take whole visual field as possible.Using the method for Corner Detection, the Corner Detection in uncalibrated image is come out, then establishes reason
Think angular coordinate, then distortion factor and center of distortion are optimized using two step optimization methods so that in fish eye images
Angular coordinate is approached by optimizing the coordinate that obtained parameter is calculated with preferable angular coordinate.Preserve distortion factor and distortion
Center.
S2, calibration cloth is put in vehicle periphery, in the image captured in each fish-eye camera, detection calibration cloth angle
Point.
The step of Corner Detection is:
1) angle point of the detection in the gridiron pattern array calibrating cloth of fish-eye camera central region;
2) using the relative position relation between big black box and gridiron pattern array, the sense for detecting big black box delimited
Interest region.Wherein, in front and rear visual angle, big black box abuts against the both sides of gridiron pattern array;And in the visual angle of left and right, it is big black
Color grid is at visual field most edge.Therefore, it is different to delimit parameter for front and rear visual angle and left and right visual angle area-of-interest;
3) image preprocessing is carried out to area-of-interest, including first carrying out self-adaption binaryzation processing, closed operation;
4) in the region of interest, using quadrangular configuration approximating method, big black box profile is positioned.In the process
In, other profiles in addition to objective contour can be generated, by limiting quadrangle position, quadrangle area, quadrangle form, phase
Adjacent side ratio, diagonal obtain black block plaid profile and four apex coordinates, on vertex than exclusive PCR quadrangular configuration
Using sub-pix angular-point detection method around coordinate, accurate black block plaid vertex position is determined.
S3, the practical corner location detected according to S2 with reference to the preferable corner location that measurement scene obtains, will come from
The image of different fish-eye cameras projects under the same coordinate system and becomes birds-eye view, establishes by the mapping of correction figure to birds-eye view
Relationship.
S4, bicycle compartment image mosaic unit in the birds-eye view that adjacent camera is converted to overlapping region carry out
All camera birds-eye views in bicycle compartment are spliced into bicycle compartment panorama birds-eye view, ultimately produce bicycle compartment by Feature Points Matching for the first time
Panorama birds-eye view and the mapping relations of each camera flake distortion figure, form of look preserve in the memory unit.
S5, after obtaining look-up table, the original of fish-eye camera acquisition is obtained from storage unit by reading lookup table mode
The mapping relation information of video pictures pixel and bicycle compartment panorama birds-eye view pixel, regards what all fish-eye cameras acquired
Frequency picture is mapped to bicycle compartment panorama birds-eye view in real time.
In practical applications, correction figure is not generated a distortion in the flake correction stage, do not generate in the perspective transform stage and singly take the photograph
As head birds-eye view, but in the image mosaic unit of bicycle compartment, bicycle compartment panorama birds-eye view is directly generated.And it is obtained for the first time
After the birds-eye view of bicycle compartment, look-up table is obtained, only needs to move according to look-up table progress image data later, so that it may directly will acquisition
Flake data be spliced into bicycle compartment birds-eye view.
S6, the adjacent camera image seam crossing in panorama birds-eye view delimit transitional region, using the side of Weighted Fusion
Method eliminates splicing seams;
It closes between camera using oblique angle as splicing seams, transitional region delimited as using two endpoints of splicing seams to be diagonal
The rectangular area on vertex.Using using the angled difference of institute, it is weighted fusion.
S7, the independent birds-eye view in each compartment on the basis of hinge joint is cut, is then spliced into static more compartment panoramas
Birds-eye view.
Forward and backward compartment birds-eye view is not cut out, and middle compartment birds-eye view in vehicle-body width direction not cut out, in length of wagon
It cuts out to front and rear hinged disk and extends to the outside a little place in direction.Allow in front compartment birds-eye view in middle compartment birds-eye view before-middle vehicle
Compartment hinge joint position overlaps, and allows in trunk birds-eye view and is overlapped with rear-middle compartment hinge joint position in middle compartment birds-eye view, spelling
It is connected in static more compartment panorama birds-eye views.
S8, hinged disk angle sensing equipment information being received by bus, parsing obtains relative angle information between compartment, according to
Hinged disk angle information rotates the independent birds-eye view in corresponding compartment, while carries out upper and lower translation to global birds-eye view, with
Adapt to screen display demand.
Middle compartment birds-eye view without rotation, front compartment according to before-middle hinged disk angle information revolves around preceding-middle hinge joint
Turn, trunk according to after-middle hinged disk angle information rotates around rear-middle hinge joint.When rotation angle is larger, front compartment or rear car
When compartment exceeds indication range, panoramic mosaic figure is whole to turning to translate in the opposite direction, and middle compartment is beyond aobvious after translation
When demonstration is enclosed, panoramic mosaic image is integrally shunk.
S9, global white balance is carried out to the image that all cameras capture, eliminates illumination effect.After each cutting
Each edge of independent compartment birds-eye view be weighted fusion, to eliminate the splicing seams of more compartment birds-eye views splicings.
The splicing line of more compartment panorama birds-eye views is the edge of middle compartment birds-eye view:It is equal to the edge of three compartment birds-eye views
The method changed using images transparent degree, using the distance away from image border as standard, transparent image border is 1, takes range image
The location transparency degree of edge a distance is 0, realizes fade effect, achievees the purpose that eliminate splicing line and seamlessly transit.
The equivalent variations made according to disclosed principle, mentality of designing or modification, the protection model in the present invention
Undeclared part within enclosing involved in the present invention is same as the prior art or is realized using the prior art.
Although having been combined embodiment to be described in detail the present invention, it should be understood by those skilled in the art that
Ground is that the present invention is not limited only to specific embodiment, on the contrary, in the various amendments without departing from the application spirit and essence, is become
Shape and replacement are all fallen among the protection domain of the application.
Claims (7)
1. it is a kind of for organizing into groups the panoramic looking-around parking assisting system of varied angle vehicle more, including fish-eye camera, hinged disk angle
Spend sensing device and data collection processor, it is characterised in that:
Panoramic looking-around parking assisting system is utilized to be at least mounted on two often saved on vehicle car or three orientation field angles
180 degree fish-eye camera acquisition video pictures and hinged disk angle sensing equipment acquisition angle information through data acquisition at
Reason device is handled to obtain the seamless spliced panoramic looking-around image in more marshalling varied angle vehicle perimeter regions;
Hinged disk angle sensing equipment is used to measure its two hinged angled information of section compartment institute in real time between compartment, using total
Line mode is connect with the data collection processor, by measured angle real-time delivery to data collection processor at
Reason.
2. according to claim 1 for organizing into groups the panoramic looking-around parking assisting system of varied angle vehicle, feature exists more
In:Data collection processor includes fish eye images distortion correction unit, Corner Detection unit, perspective transform unit, bicycle compartment figure
As concatenation unit, bicycle compartment image fusion unit, hinged disk angle acquisition unit, more compartment image mosaic units, more compartment figures
As integrated unit;Wherein:
Fish eye images distortion correction unit is used for the internal structure according to each fish-eye camera and the distortion model of foundation, demarcates
To camera parameter and distortion correction parameter, the mapping relations from fish eye images to distortion correction image are obtained;
In the image that Corner Detection unit is captured in each fish-eye camera, detection calibration cloth angle point;Perspective transform unit root
The practical corner location that the preferable corner location and detection obtained according to measurement scene obtains, will be from different fish-eye cameras
Image projects under the same coordinate system and becomes birds-eye view, establishes by the mapping relations of correction figure to birds-eye view;
Bicycle compartment image mosaic unit, for the overlapping region progress spy in the birds-eye view that adjacent camera is converted to
All camera birds-eye views in bicycle compartment are spliced into bicycle compartment panorama birds-eye view, ultimately produce bicycle compartment panorama bird by sign point matching
The mapping relations for figure and each camera flake distortion figure of looking down from a height, generate and preserve look-up table;
Bicycle compartment image fusion unit for the adjacent camera image seam crossing in panorama birds-eye view, delimited transitional region, adopted
With the method for Weighted Fusion, splicing seams are eliminated;
Hinged disk angle acquisition unit is connect by bus with hinged disk angle sensing equipment, receives and parses through relative angle between compartment
Spend information;
The independent birds-eye view in each compartment on the basis of hinge joint, is cut and is spliced, according to hinge by more compartment image mosaic units
It connects disk angle information to rotate the independent birds-eye view in corresponding compartment, while upper and lower translation is carried out to global birds-eye view, with suitable
Answer screen display demand;
More compartment image fusion units carry out each camera global white balance, to the independent compartment birds-eye view after each cutting
Each edge be weighted fusion, to eliminate the splicing seams of more compartment birds-eye views splicing.
3. the method demarcated and spliced using more marshalling varied angle vehicle panoramic viewing systems described in claim 1,
It is characterized in that, specifically includes following steps:
S1, fish eye images distortion correction unit are used for according to the internal structure of each fish-eye camera and the distortion model of foundation, mark
Surely camera parameter and distortion correction parameter are obtained, obtains the mapping relations from fish eye images to distortion correction image;
In S2, the image captured in each fish-eye camera, detection calibration cloth angle point;
S3, the practical corner location detected according to S2 with reference to the preferable corner location that measurement scene obtains, will come from difference
The image of fish-eye camera projects under the same coordinate system and becomes birds-eye view, establishes by the mapping relations of correction figure to birds-eye view;
S4, bicycle compartment image mosaic unit are to the overlapping region progress feature in the birds-eye view that adjacent camera is converted to
All camera birds-eye views in bicycle compartment are spliced into bicycle compartment panorama birds-eye view, ultimately produce bicycle compartment panorama by point matching for the first time
Birds-eye view and the mapping relations of each camera flake distortion figure, form of look preserve in the memory unit;
S5, after obtaining look-up table, the original video that fish-eye camera acquires is obtained by reading lookup table mode from storage unit
The mapping relation information of picture photo vegetarian refreshments and bicycle compartment panorama birds-eye view pixel, the video that all fish-eye cameras are acquired are drawn
Face is mapped to bicycle compartment panorama birds-eye view in real time;
S6, the adjacent camera image seam crossing in panorama birds-eye view delimit transitional region, using the method for Weighted Fusion, disappear
Except splicing seams;
S7, the independent birds-eye view in each compartment on the basis of hinge joint is cut, is then spliced into static more compartment panoramas and gets a bird's eye view
Figure.
S8, hinged disk angle sensing equipment information is received by bus, parsing obtains relative angle information between compartment, according to hinged
Disk angle information rotates the independent birds-eye view in corresponding compartment, while carries out upper and lower translation to global birds-eye view, to adapt to
Screen display demand;
S9, global white balance is carried out to the image that all cameras capture, eliminates illumination effect;To the list after each cutting
Each edge of only compartment birds-eye view is weighted fusion, to eliminate the splicing seams of more compartment birds-eye view splicings.
4. the method that more marshalling varied angle vehicle panoramic viewing systems described in 3 is wanted to be demarcated and spliced using right, special
Sign is that the S1 is used as camera distortion model using multinomial model, and tessellated fish-eye image is included using single width
As completing camera calibration.
5. the method that more marshalling varied angle vehicle panoramic viewing systems described in 3 is wanted to be demarcated and spliced using right, special
Sign is that the S2 detects the angle point in the gridiron pattern array calibrating cloth of fish-eye camera central region first, then
The area-of-interest for detecting visual field both sides black block plaid delimited according to part corner location, in the region of interest into
Row quadrangle is fitted, by limiting quadrangle position, quadrangle area, quadrangle form, adjacent side ratio, diagonal than excluding
Quadrangular configuration is interfered, obtains black block plaid profile and four apex coordinates, sub-pix angle is used around apex coordinate
Point detecting method determines black block plaid vertex position.
6. want the method that the 3 more marshalling varied angle vehicle panoramic viewing systems stated are demarcated and spliced, feature using right
Be, in the S7, front compartment, trunk birds-eye view are not cut out, middle compartment birds-eye view not cut out in vehicle-body width direction,
Allow in front compartment birds-eye view in middle compartment birds-eye view before-middle compartment hinge joint position overlaps, allow in trunk birds-eye view with
Rear-middle compartment hinge joint position in middle compartment birds-eye view overlaps, and is spliced into static more compartment panorama birds-eye views.
7. want the method that the 3 more marshalling varied angle vehicle panoramic viewing systems stated are demarcated and spliced, feature using right
Be, in the S8, compartment birds-eye view without rotation, front compartment according to before-middle hinged disk angle information is around preceding-middle hinge joint
Rotation, trunk according to after-middle hinged disk angle information rotates around rear-middle hinge joint;Current compartment or trunk are beyond display
During range, panoramic mosaic figure is integrally translated in the opposite direction to turn, it, will when middle compartment exceeds indication range after translation
Panoramic mosaic image is integrally shunk.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810074955.XA CN108263283B (en) | 2018-01-25 | 2018-01-25 | Method for calibrating and splicing panoramic all-round looking system of multi-marshalling variable-angle vehicle |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810074955.XA CN108263283B (en) | 2018-01-25 | 2018-01-25 | Method for calibrating and splicing panoramic all-round looking system of multi-marshalling variable-angle vehicle |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108263283A true CN108263283A (en) | 2018-07-10 |
CN108263283B CN108263283B (en) | 2020-01-14 |
Family
ID=62776812
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810074955.XA Active CN108263283B (en) | 2018-01-25 | 2018-01-25 | Method for calibrating and splicing panoramic all-round looking system of multi-marshalling variable-angle vehicle |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108263283B (en) |
Cited By (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109544647A (en) * | 2018-11-30 | 2019-03-29 | 郑州天迈科技股份有限公司 | Calibration cloth, place and method for 360 ° of panoramic parking assist systems |
CN109532671A (en) * | 2018-12-12 | 2019-03-29 | 广州小鹏汽车科技有限公司 | Track of vehicle processing method, device, electronic equipment and automobile |
CN109767473A (en) * | 2018-12-30 | 2019-05-17 | 惠州华阳通用电子有限公司 | A kind of panorama parking apparatus scaling method and device |
CN109905613A (en) * | 2019-01-21 | 2019-06-18 | 广州市安晓科技有限责任公司 | A kind of auto-panorama joining method, device and medium for evading interference of opening the door |
CN110060200A (en) * | 2019-03-18 | 2019-07-26 | 阿里巴巴集团控股有限公司 | Perspective image transform method, device and equipment |
CN110363085A (en) * | 2019-06-10 | 2019-10-22 | 浙江零跑科技有限公司 | A kind of heavy articulator based on hinged angle compensation looks around implementation method |
CN110378201A (en) * | 2019-06-05 | 2019-10-25 | 浙江零跑科技有限公司 | A kind of hinged angle measuring method of multiple row vehicle based on side ring view fisheye camera input |
CN110719411A (en) * | 2019-12-16 | 2020-01-21 | 长沙智能驾驶研究院有限公司 | Panoramic all-around view image generation method of vehicle and related equipment |
CN110751598A (en) * | 2019-10-17 | 2020-02-04 | 长沙智能驾驶研究院有限公司 | Vehicle hinge point coordinate calibration method and device, computer equipment and storage medium |
CN110781883A (en) * | 2019-09-18 | 2020-02-11 | 江苏大学 | Parking space size identification system and method based on 360-degree all-round-looking camera |
CN110826364A (en) * | 2018-08-09 | 2020-02-21 | 上海汽车集团股份有限公司 | Stock position identification method and device |
CN111179168A (en) * | 2019-12-12 | 2020-05-19 | 郑州嘉晨电器有限公司 | Vehicle-mounted 360-degree panoramic all-around monitoring system and method |
CN111369439A (en) * | 2020-02-29 | 2020-07-03 | 华南理工大学 | Panoramic view image real-time splicing method for automatic parking stall identification based on panoramic view |
CN111361502A (en) * | 2020-03-23 | 2020-07-03 | 长沙立中汽车设计开发股份有限公司 | Implementation method for variable-angle panoramic looking-around system of articulated engineering vehicle |
CN111546986A (en) * | 2020-04-30 | 2020-08-18 | 北京大椽科技有限公司 | Trailer panoramic looking-around method |
CN111559314A (en) * | 2020-04-27 | 2020-08-21 | 长沙立中汽车设计开发股份有限公司 | Depth and image information fused 3D enhanced panoramic looking-around system and implementation method |
CN111856871A (en) * | 2019-04-26 | 2020-10-30 | 东莞潜星电子科技有限公司 | Vehicle-mounted 3D panoramic all-around display method |
CN111912374A (en) * | 2019-05-08 | 2020-11-10 | 中车株洲电力机车研究所有限公司 | Vehicle articulation angle measuring system and method and application vehicle |
CN112793564A (en) * | 2021-02-07 | 2021-05-14 | 杨东杰 | Autonomous parking auxiliary system based on panoramic aerial view and deep learning |
CN112793509A (en) * | 2021-04-14 | 2021-05-14 | 天津所托瑞安汽车科技有限公司 | Blind area monitoring method and device, equipment and medium |
CN112967183A (en) * | 2021-01-30 | 2021-06-15 | 惠州华阳通用电子有限公司 | Panoramic picture splicing method and storage medium |
CN113255468A (en) * | 2021-05-06 | 2021-08-13 | 东风汽车集团股份有限公司 | Vehicle-mounted panoramic image calibration block identification optimization method and system and readable storage medium |
CN113538377A (en) * | 2021-07-15 | 2021-10-22 | 河北三国新能源科技有限公司 | Driving test vehicle quarter turn line pressing detection method and system based on panoramic looking-around |
CN113870101A (en) * | 2021-12-02 | 2021-12-31 | 交通运输部公路科学研究所 | Panoramic all-around image splicing method and device for articulated vehicle |
WO2022057077A1 (en) * | 2020-09-15 | 2022-03-24 | 徐工集团工程机械股份有限公司道路机械分公司 | Hinged engineering machinery, panoramic surround-view system and calibration method thereof |
CN115412676A (en) * | 2022-09-13 | 2022-11-29 | 清华大学 | Panoramic looking-around system based on weight mask and panoramic image fusion method |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103763517A (en) * | 2014-03-03 | 2014-04-30 | 惠州华阳通用电子有限公司 | Vehicle-mounted around view display method and system |
CN104732542A (en) * | 2015-03-27 | 2015-06-24 | 安徽省道一电子科技有限公司 | Image processing method for panoramic vehicle safety system based on multi-camera self calibration |
CN104851076A (en) * | 2015-05-27 | 2015-08-19 | 武汉理工大学 | Panoramic 360-degree-view parking auxiliary system for commercial vehicle and pick-up head installation method |
CN105096317A (en) * | 2015-07-03 | 2015-11-25 | 吴晓军 | Fully automatic calibration method for high performance camera under complicated background |
CN106408511A (en) * | 2016-09-22 | 2017-02-15 | 苏州大学 | Overlook conversion method, overlook image acquisition method and mapping table construction method of fisheye image |
CN107154022A (en) * | 2017-05-10 | 2017-09-12 | 北京理工大学 | A kind of dynamic panorama mosaic method suitable for trailer |
-
2018
- 2018-01-25 CN CN201810074955.XA patent/CN108263283B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103763517A (en) * | 2014-03-03 | 2014-04-30 | 惠州华阳通用电子有限公司 | Vehicle-mounted around view display method and system |
CN104732542A (en) * | 2015-03-27 | 2015-06-24 | 安徽省道一电子科技有限公司 | Image processing method for panoramic vehicle safety system based on multi-camera self calibration |
CN104851076A (en) * | 2015-05-27 | 2015-08-19 | 武汉理工大学 | Panoramic 360-degree-view parking auxiliary system for commercial vehicle and pick-up head installation method |
CN105096317A (en) * | 2015-07-03 | 2015-11-25 | 吴晓军 | Fully automatic calibration method for high performance camera under complicated background |
CN106408511A (en) * | 2016-09-22 | 2017-02-15 | 苏州大学 | Overlook conversion method, overlook image acquisition method and mapping table construction method of fisheye image |
CN107154022A (en) * | 2017-05-10 | 2017-09-12 | 北京理工大学 | A kind of dynamic panorama mosaic method suitable for trailer |
Cited By (40)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110826364B (en) * | 2018-08-09 | 2024-02-02 | 上海汽车集团股份有限公司 | Library position identification method and device |
CN110826364A (en) * | 2018-08-09 | 2020-02-21 | 上海汽车集团股份有限公司 | Stock position identification method and device |
CN109544647A (en) * | 2018-11-30 | 2019-03-29 | 郑州天迈科技股份有限公司 | Calibration cloth, place and method for 360 ° of panoramic parking assist systems |
CN109532671A (en) * | 2018-12-12 | 2019-03-29 | 广州小鹏汽车科技有限公司 | Track of vehicle processing method, device, electronic equipment and automobile |
CN109767473B (en) * | 2018-12-30 | 2022-10-28 | 惠州华阳通用电子有限公司 | Panoramic parking device calibration method and device |
CN109767473A (en) * | 2018-12-30 | 2019-05-17 | 惠州华阳通用电子有限公司 | A kind of panorama parking apparatus scaling method and device |
CN109905613A (en) * | 2019-01-21 | 2019-06-18 | 广州市安晓科技有限责任公司 | A kind of auto-panorama joining method, device and medium for evading interference of opening the door |
CN110060200A (en) * | 2019-03-18 | 2019-07-26 | 阿里巴巴集团控股有限公司 | Perspective image transform method, device and equipment |
CN110060200B (en) * | 2019-03-18 | 2023-05-30 | 创新先进技术有限公司 | Image perspective transformation method, device and equipment |
CN111856871A (en) * | 2019-04-26 | 2020-10-30 | 东莞潜星电子科技有限公司 | Vehicle-mounted 3D panoramic all-around display method |
CN111912374A (en) * | 2019-05-08 | 2020-11-10 | 中车株洲电力机车研究所有限公司 | Vehicle articulation angle measuring system and method and application vehicle |
CN110378201A (en) * | 2019-06-05 | 2019-10-25 | 浙江零跑科技有限公司 | A kind of hinged angle measuring method of multiple row vehicle based on side ring view fisheye camera input |
CN110363085B (en) * | 2019-06-10 | 2021-11-09 | 浙江零跑科技股份有限公司 | Method for realizing looking around of heavy articulated vehicle based on articulation angle compensation |
CN110363085A (en) * | 2019-06-10 | 2019-10-22 | 浙江零跑科技有限公司 | A kind of heavy articulator based on hinged angle compensation looks around implementation method |
CN110781883A (en) * | 2019-09-18 | 2020-02-11 | 江苏大学 | Parking space size identification system and method based on 360-degree all-round-looking camera |
CN110781883B (en) * | 2019-09-18 | 2024-03-19 | 江苏大学 | Parking space size recognition system and method based on 360-degree looking-around camera |
CN110751598A (en) * | 2019-10-17 | 2020-02-04 | 长沙智能驾驶研究院有限公司 | Vehicle hinge point coordinate calibration method and device, computer equipment and storage medium |
CN110751598B (en) * | 2019-10-17 | 2023-09-26 | 长沙智能驾驶研究院有限公司 | Vehicle hinge point coordinate calibration method and device, computer equipment and storage medium |
WO2021073634A1 (en) * | 2019-10-17 | 2021-04-22 | 长沙智能驾驶研究院有限公司 | Method for vehicle hinge point calibration and corresponding calibration apparatus, computer device, and storage medium |
CN111179168A (en) * | 2019-12-12 | 2020-05-19 | 郑州嘉晨电器有限公司 | Vehicle-mounted 360-degree panoramic all-around monitoring system and method |
CN111179168B (en) * | 2019-12-12 | 2023-11-17 | 河南嘉晨智能控制股份有限公司 | Vehicle-mounted 360-degree panoramic all-around monitoring system and method |
CN110719411B (en) * | 2019-12-16 | 2020-04-03 | 长沙智能驾驶研究院有限公司 | Panoramic all-around view image generation method of vehicle and related equipment |
WO2021121251A1 (en) * | 2019-12-16 | 2021-06-24 | 长沙智能驾驶研究院有限公司 | Method and device for generating vehicle panoramic surround view image |
US11843865B2 (en) | 2019-12-16 | 2023-12-12 | Changsha Intelligent Driving Institute Corp., Ltd | Method and device for generating vehicle panoramic surround view image |
CN110719411A (en) * | 2019-12-16 | 2020-01-21 | 长沙智能驾驶研究院有限公司 | Panoramic all-around view image generation method of vehicle and related equipment |
CN111369439A (en) * | 2020-02-29 | 2020-07-03 | 华南理工大学 | Panoramic view image real-time splicing method for automatic parking stall identification based on panoramic view |
CN111369439B (en) * | 2020-02-29 | 2023-05-23 | 华南理工大学 | Panoramic all-around image real-time splicing method for automatic parking space identification based on all-around |
CN111361502A (en) * | 2020-03-23 | 2020-07-03 | 长沙立中汽车设计开发股份有限公司 | Implementation method for variable-angle panoramic looking-around system of articulated engineering vehicle |
CN111559314A (en) * | 2020-04-27 | 2020-08-21 | 长沙立中汽车设计开发股份有限公司 | Depth and image information fused 3D enhanced panoramic looking-around system and implementation method |
CN111546986A (en) * | 2020-04-30 | 2020-08-18 | 北京大椽科技有限公司 | Trailer panoramic looking-around method |
WO2022057077A1 (en) * | 2020-09-15 | 2022-03-24 | 徐工集团工程机械股份有限公司道路机械分公司 | Hinged engineering machinery, panoramic surround-view system and calibration method thereof |
CN112967183A (en) * | 2021-01-30 | 2021-06-15 | 惠州华阳通用电子有限公司 | Panoramic picture splicing method and storage medium |
CN112793564A (en) * | 2021-02-07 | 2021-05-14 | 杨东杰 | Autonomous parking auxiliary system based on panoramic aerial view and deep learning |
CN112793564B (en) * | 2021-02-07 | 2022-07-22 | 杨东杰 | Autonomous parking auxiliary system based on panoramic aerial view and deep learning |
CN112793509A (en) * | 2021-04-14 | 2021-05-14 | 天津所托瑞安汽车科技有限公司 | Blind area monitoring method and device, equipment and medium |
CN113255468A (en) * | 2021-05-06 | 2021-08-13 | 东风汽车集团股份有限公司 | Vehicle-mounted panoramic image calibration block identification optimization method and system and readable storage medium |
CN113538377B (en) * | 2021-07-15 | 2022-08-12 | 河北三国新能源科技有限公司 | Driving test vehicle quarter turn line pressing detection method and system based on panoramic looking-around |
CN113538377A (en) * | 2021-07-15 | 2021-10-22 | 河北三国新能源科技有限公司 | Driving test vehicle quarter turn line pressing detection method and system based on panoramic looking-around |
CN113870101A (en) * | 2021-12-02 | 2021-12-31 | 交通运输部公路科学研究所 | Panoramic all-around image splicing method and device for articulated vehicle |
CN115412676A (en) * | 2022-09-13 | 2022-11-29 | 清华大学 | Panoramic looking-around system based on weight mask and panoramic image fusion method |
Also Published As
Publication number | Publication date |
---|---|
CN108263283B (en) | 2020-01-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108263283A (en) | More marshalling varied angle vehicle panoramic viewing system calibration and joining method | |
CN109435852B (en) | Panoramic auxiliary driving system and method for large truck | |
CN104851076B (en) | Panoramic looking-around parking assisting system and camera installation method for commercial car | |
CN110381255B (en) | Vehicle-mounted video monitoring system and method applying 360-degree panoramic looking-around technology | |
CN104512328B (en) | Automobile looks around image generating method and automobile viewing system | |
US10701300B2 (en) | Display system and method | |
CN109741455B (en) | Vehicle-mounted stereoscopic panoramic display method, computer readable storage medium and system | |
CN108621948A (en) | Vehicle panoramic viewing system and panoramic looking-around image generating method | |
CN108765496A (en) | A kind of multiple views automobile looks around DAS (Driver Assistant System) and method | |
CN103810686A (en) | Seamless splicing panorama assisting driving system and method | |
CN103617606A (en) | Vehicle multi-angle panorama generating method for aided driving | |
CN109087251B (en) | Vehicle-mounted panoramic image display method and system | |
CN105321160B (en) | The multi-camera calibration that 3 D stereo panorama is parked | |
CN103802725B (en) | A kind of new vehicle carried driving assistant images generation method | |
CN109429039A (en) | A kind of mostly marshalling articulated vehicle circumference video panorama display system and method | |
CN109948398A (en) | The image processing method and panorama parking apparatus that panorama is parked | |
CN106994936A (en) | A kind of 3D panoramic parking assist systems | |
CN101442618A (en) | Method for synthesizing 360 DEG ring-shaped video of vehicle assistant drive | |
CN112224132A (en) | Vehicle panoramic all-around obstacle early warning method | |
CN110363085B (en) | Method for realizing looking around of heavy articulated vehicle based on articulation angle compensation | |
CN109767473A (en) | A kind of panorama parking apparatus scaling method and device | |
CN110626269A (en) | Intelligent imaging driving assistance system and method based on intention identification fuzzy control | |
CN115239922A (en) | AR-HUD three-dimensional coordinate reconstruction method based on binocular camera | |
CN208715087U (en) | Vehicle panoramic viewing system | |
CN104504677B (en) | A kind of image generating method based on variable visual angle |
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 |