CN107492125A - The processing method of automobile fish eye lens panoramic view picture - Google Patents
The processing method of automobile fish eye lens panoramic view picture Download PDFInfo
- Publication number
- CN107492125A CN107492125A CN201710632300.5A CN201710632300A CN107492125A CN 107492125 A CN107492125 A CN 107492125A CN 201710632300 A CN201710632300 A CN 201710632300A CN 107492125 A CN107492125 A CN 107492125A
- Authority
- CN
- China
- Prior art keywords
- automobile
- eye lens
- fish eye
- processing method
- parameter
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 241000251468 Actinopterygii Species 0.000 title claims abstract description 48
- 238000003672 processing method Methods 0.000 title claims abstract description 15
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 10
- 239000011159 matrix material Substances 0.000 claims description 10
- 230000009466 transformation Effects 0.000 claims description 10
- 230000002093 peripheral effect Effects 0.000 claims description 4
- 241000208340 Araliaceae Species 0.000 description 5
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 5
- 235000003140 Panax quinquefolius Nutrition 0.000 description 5
- 235000008434 ginseng Nutrition 0.000 description 5
- 238000000034 method Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000002845 discoloration Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/02—Affine transformations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/04—Context-preserving transformations, e.g. by using an importance map
- G06T3/047—Fisheye or wide-angle transformations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The invention provides a kind of processing method of automobile fish eye lens panoramic view picture, left side, right side, headstock and the tailstock on automobile are provided with fish eye lens, including step：Step S10, obtain the uncalibrated image with scaling board that fish eye lens photographs；Step S20, Taylor polynomial model function is built based on the uncalibrated image, to calculate fish-eye inside and outside parameter；Step S30, it is based on the inside and outside parameter that coordinate system residing for each demarcation version of automobile surrounding is unified into vehicle body coordinate system, and the realtime graphic that fish eye lens is shot is synthesized to form auto-panorama image.The present invention solves the technical problem for utilizing fault image caused by fish eye lens captured in real-time panoramic picture on automobile in the prior art.
Description
Technical field
The invention belongs to automobile electronic information processing technology field, more particularly to a kind of automobile fish eye lens panoramic view as
Processing method.
Background technology
At present, the camera on existing automobile largely uses fish eye lens, and fish eye lens belongs to ultra-wide angle mirror
Head, focal length is small, and general satisfaction focal length is smaller, the bigger rule of corresponding wide-angle.Fish eye lens has the considerably long depth of field, for non-
Often closely arriving unlimited far object can blur-free imaging.But the picture captured by fish eye lens is as a rule barrel distortion,
The characteristics of barrel distortion is that picture centre distortion is small, and both sides distortion is bigger, and this distortion influences whether driver for automobile
The understanding of surrounding road condition, very big potential safety hazard be present.
Therefore, prior art is to be improved.
The content of the invention
It is a primary object of the present invention to propose a kind of processing method of automobile fish eye lens panoramic view picture, it is intended to solve existing
There is automobile in technology to use the technical problem of the panorama realtime graphic of fish eye lens generation distortion.
In order to solve the above technical problems, the processing method of the automobile fish eye lens panoramic view picture of the present invention, the left side on automobile
Side, right side, headstock and the tailstock are provided with fish eye lens, including step：
Step S10, obtain the uncalibrated image with scaling board that fish eye lens photographs；
Step S20, Taylor polynomial model function is built based on the uncalibrated image, to calculate fish-eye inside and outside ginseng
Number；
Step S30, coordinate system residing for each demarcation version of automobile surrounding is uniformly arrived by vehicle body coordinate based on the inside and outside parameter
In system, and the realtime graphic that fish eye lens is shot is synthesized to form auto-panorama image.
Preferably, step is included before step S10：
Step S1, four demarcation versions are placed respectively in the predeterminated position of peripheral vehicle.
Preferably, the inside and outside parameter includes inner parameter and external parameter, and the external parameter includes affine transformation square
Battle array A and motion vector t, inner parameter include Taylor expansion multinomial coefficient a0, a2... ... and aN。
Preferably, the step S20 includes step：
Step S21, extract the distortion point coordinate information on uncalibrated image；
Step S22, the Taylor polynomial model functional minimum value is minimized according to distortion point coordinate information, to solve
Go out inner parameter and external parameter.
Preferably, the demarcation version is square plate, includes black block and white blocks on square plate, every piece of black block or
Every piece of white blocks are not in contact with its own color identical color lump.
Preferably, the step S30 includes step：
Step S31, based on the affine transformation matrix A by coordinate system direction corresponding to each demarcation version of automobile surrounding with
It is identical to demarcate version coordinate system direction；
Step S32, based on the motion vector t by coordinate origin corresponding to each demarcation version of the automobile surrounding with
Vehicle axis system origin overlaps；
Step S33, the realtime graphic taken by each fish eye lens on automobile is spliced, to form complete vapour
Car panoramic picture.
The processing method of the automobile fish eye lens panoramic view picture of the present invention has the advantages that：
1st, projective invariant point quantity is reduced；
2nd, amount of calculation is small, and processing speed is fast；
3rd, the tool construction utilized is simple, and cost is low.
Brief description of the drawings
Fig. 1 is the schematic flow sheet of first embodiment of the invention；
Fig. 2 is the schematic flow sheet of second embodiment of the invention；
Fig. 3 is the schematic flow sheet of the refinement step of the step S20 in the embodiment of the present invention；
Fig. 4 is the schematic flow sheet of the refinement step of the step S30 in the embodiment of the present invention；
Fig. 5 is the schematic flow sheet of the refinement step of the step S33 in the embodiment of the present invention.
The realization, functional characteristics and advantage of the object of the invention will be described further referring to the drawings in conjunction with the embodiments.
Embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
With reference to figure 1, Fig. 1 is the schematic flow sheet of first embodiment of the invention.
As shown in figure 1, the processing method of the automobile fish eye lens panoramic view picture of the present invention, left side, right side on automobile, car
Head and the tailstock are provided with fish eye lens, including step：
Step S10, obtain the uncalibrated image with scaling board that fish eye lens photographs；
In step slo, car-mounted terminal obtains the flake of the left side being arranged on automobile, right side, headstock and tailstock position
The image of lens shooting, wherein in advance in the surrounding of automobile, i.e., the left side of automobile, right side, before headstock and behind the tailstock respectively
The plate for demarcation is placed, the image of acquisition includes the uncalibrated image containing scaling board.What demarcation represented is to utilize some equipment
Determine the input/output relation of fish-eye sensor.
Step S20, Taylor polynomial model function is built based on the uncalibrated image, to calculate fish-eye inside and outside ginseng
Number；
After execution of step S10, step S20 is performed, the uncalibrated image with scaling board obtained based on step S10,
It can be brought into by the coordinate information extracted on uncalibrated image in the Taylor polynomial model function being preset in car-mounted terminal
Solved, and obtain fish-eye inside and outside parameter.Using Taylor polynomial model function for fish eye lens inside and outside parameter
It is simple with step compared to prior art in solution procedure, the small advantage of amount of calculation.
Step S30, coordinate system residing for each demarcation version of automobile surrounding is uniformly arrived by vehicle body coordinate based on the inside and outside parameter
In system, and the realtime graphic that fish eye lens is shot is synthesized to form auto-panorama image.
After execution of step S20, according to fish-eye inside and outside parameter, by coordinate system residing for each scaling board of surrounding
Calculated, coordinate system where each scaling board is overlapped with vehicle axis system, then by the image of fish eye lens captured in real-time
Synthesized, form complete auto-panorama image.In the present embodiment, by being demarcated to fish eye lens, inside and outside join is obtained
Number, and unified coordinate system to be to form complete auto-panorama image, compared to prior art, this image processing method amount of calculation
Small, cost is low, and acquired pattern distortion point quantity is few.
With reference to figure 2, Fig. 2 is the schematic flow sheet of second embodiment of the invention.
As shown in Figure 2, it is preferable that include step before step S10：
Step S1, four demarcation versions are placed respectively in the predeterminated position of peripheral vehicle.
This step S1 is performed before step S10, places four demarcation respectively in the predeterminated position of peripheral vehicle in advance
Plate, wherein, predeterminated position include apart from headstock at least 10mm positions, apart from the tailstock at least 10mm positions, on the left of the car at least
10mm positions and at least 10mm positions on the right side of the car.To ensure that it is higher that the fish eye lens of each position can photograph integrity degree
Image with scaling board, reduce the time spent to fish eye lens adjustment.As the optimization of the present embodiment, step S1 it
Before, in addition to step：The tire pressure of monitoring automobile tire in advance, if meeting default tire pressure, perform step S1.So way is favourable
In ensuring the tire pressure of automobile in normal level, in order to avoid influence the accuracy of follow-up calibration parameter.
Preferably, the inside and outside parameter includes inner parameter and external parameter, and the external parameter includes affine transformation square
Battle array A and motion vector t, inner parameter include Taylor expansion multinomial coefficient a0, a2... ... and aN.The present embodiment is to inside and outside ginseng
Number is specific to be limited, the affine transformation matrix A and motion vector t of external parameter and the Taylor expansion multinomial coefficient of inner parameter
a0, a2... ... and aN.By these parameters, the coincidence of coordinate system is realized.Below, by for the external parameter in the present embodiment
Affine transformation matrix A and motion vector t and inner parameter Taylor expansion multinomial coefficient a0, a2... ... and aNCalculating process
It is illustrated：Parameter A is affine transformation matrix, describes the plane of delineation and ideal transducer Plane Installation error.Motion vector t
Describe the image coordinate (X of fish eye images center of distortionc, Yc) position skew.First, it is assumed that in u'=Au "+t (2-2) formula
A is unit matrix, i.e. the plane of delineation overlaps with ideal transducer plane.And assume fisheye camera image and optical axes crosspoint OcWith
The center I of imagecOverlap.That is Oc=Ic, t=α (Oc-Ic)=0；According to this initial value it is assumed that there is u "=u', convolution g
(u ", v ")=(u ", v ", f (u ", v "))T(2-4), f (u ", v ")=a0+a1ρ”+a2ρ”2+...+aNρ”N(2-5) is brought intoFollowing projection equation is obtained in formula
U' herein, v' are with picture centre IcFor origin, pixel is the coordinate of unit.ρ ' is Euclidean distance.Therefore only need
Want N number of parameter (a0, a2... ... and aN) need to be estimated.
Calibration process is that the plane reference plate of known physical dimension is positioned over to different position shooting images.Scaling board
Diverse location reflects different outer ginsengs, i.e. spin matrix R=[r1,r2,r3] and translation vector t.Assuming that IiFor a certain scaling board
Shooting image, Mij=[Xij,Yij,Zij] be angle point j on scaling board i under scaling board coordinate system (world coordinate system) coordinate
Value, mij=[uij,vij]TFor the pixel coordinate value of correspondence image plane.As it is assumed that scaling board is plane, for without loss of generality,
We make Zij=0, then equation (2-9) turn to
Therefore for the solution of fish eye lens demarcation, different scaling board photo external parameters are needed to determine respectively.
(1) camera external parameter is solved
By (2-10) formula both ends difference premultiplication vector pij, eliminate λ and obtain
According to (2-10), 3 homogeneous equations can be obtained,
vj·(r31Xj+r32Yj+t3)-f(ρj)·(r21Xj+r22Yj+t2)=0 (2-12)
f(ρj)·(r11Xj+r12Yj+t1)-uj·(r31Xj+r32Yj+t3)=0 (2-13)
uj·(r21Xj+r22Yj+t2)-vj·(r11Xj+r12Yj+t1)=0 (2-14)
Here Xj, YjAnd uj, vjIt is known.More than observation three formulas, only (2-14) is on r11, r12, r21, r22, t1And t2
Linear equation.Assuming that there is L angle point on scaling board, L angle on scaling board is arranged respectively and writes equation (2-14), and is rewritten as square
Battle array expression-form.
MH=0 (2-15)
Wherein, H=[r11,r12,r21,r22,t1,t2]T
The Linear Estimation of vectorial H values can minimize according to criterion of least squares | | MH | |2Obtain, wherein meeting | | H
||2=1.This can be realized by using SVD.Due to r1,r2It is normal orthogonal, r31And r32It can also uniquely determine.
Each uncalibrated image be resulting in except t3Outer parameter r11,r12,r21,r22,r31,r32,t1,t2。t3Will be
It is calculated below when estimated projection function.
(2) internal reference of camera is solved
The outer ginseng of camera is solved previously by formula (2-14).The external parameter value of estimation is brought into equation (2- now
12) and (2-13) asks for the camera internal parameter a for being described as projection function g0, a2... ... and aN.At the same time, calculate every
Open uncalibrated imageAssuming that there is K scaling board images, it is below equation group that we, which merge (2-12) (2-13),
Wherein
The least square solution of overdetermined equation is obtained finally by using pseudoinverse, obtains the inner parameter for descriptive model
a0,a2,...,aN。
With reference to figure 3, Fig. 3 is the schematic flow sheet of the refinement step of the step S20 in the embodiment of the present invention.
As shown in Figure 3, it is preferable that the step S20 includes step：
Step S21, extract the distortion point coordinate information on uncalibrated image；
Step S22, the Taylor polynomial model functional minimum value is minimized according to distortion point coordinate information, to solve
Go out inner parameter and external parameter.
In the step s 21, the distortion point coordinate information on uncalibrated image is extracted, by the distortion point on each scaling board
Heart point coordinates is sent on car-mounted terminal, and car-mounted terminal is brought into center point coordinate in Taylor polynomial model function, passes through
Iteration carries out minimum operation, to solve fish eye lens inner parameter and external parameter.It is excellent in the calculation procedure of the present embodiment
Gesture is, the uncalibrated image that fish eye lens is sent, the uncalibrated image with complete scaling board is not limited to, suitable for flake mirror
The incomplete uncalibrated image with scaling board that hair is brought, i.e., described uncalibrated image include incomplete scaling board, lead to
It is strong and less demanding for scaling board putting position with property.
Preferably, the demarcation version is square plate, includes black block and white blocks on square plate, every piece of black block or
Every piece of white blocks are not in contact with its own color identical color lump.The present embodiment carries out structure qualification to scaling board, in order to
Demarcated, black block and the alternate of white blocks are situated so as to extract distortion point coordinate information.
With reference to figure 4, Fig. 4 is the schematic flow sheet of the refinement step of the step S30 in the embodiment of the present invention.
As shown in Figure 4, it is preferable that the step S30 includes step：
Step S31, based on the affine transformation matrix A by coordinate system direction corresponding to each demarcation version of automobile surrounding with
It is identical to demarcate version coordinate system direction；
Step S32, based on the motion vector t by coordinate origin corresponding to each demarcation version of the automobile surrounding with
Vehicle axis system origin overlaps；
Step S33, the realtime graphic taken by each fish eye lens on automobile is spliced, to form complete vapour
Car panoramic picture.
In the present embodiment, the method for unified coordinate system is defined, first by affine transformation matrix A and each scaling board
Corresponding coordinate system is multiplied, that is, realizes that coordinate system direction is identical with vehicle axis system direction corresponding to each scaling board；Then will
Motion vector adds coordinate system corresponding to each scaling board, that is, realizes that coordinate origin on automobile with sitting corresponding to each scaling board
Mark system origin overlaps；Finally the image mosaic of fish eye lens captured in real-time is got up, to form complete auto-panorama image.As
The optimization of the present embodiment, with reference to figure 5, step S33 includes step：
Step S34, judge that the realtime graphic that each fish eye lens sends over whether there is overlapping region；
Step S35, if nothing, the realtime graphic taken by each fish eye lens is spliced, to form complete vapour
Car panoramic picture.
Step S36, if so, then being merged the pixel of overlapping region and real-time captured by each fish eye lens
Image is spliced to form complete auto-panorama image.
In the present embodiment, the realtime graphic in advance sending over each fish eye lens carries out once simulation splicing, judges
With the presence or absence of overlapping region；If there is overlapping region, the pixel of overlapping region is merged, pixel weight is reduced to reach
Fold and cause the technical problem of discoloration, after pixel fusion is completed, the realtime graphic captured by each fish eye lens is carried out
Splice to form complete auto-panorama image.In the present embodiment, the part weight caused by after each realtime graphic splices is avoided
Folded area's color depth technical problem, more they tends to picture true to nature and normal.
The preferred embodiments of the present invention are these are only, are not intended to limit the scope of the invention, it is every to utilize this hair
The equivalent structure or equivalent flow conversion that bright specification and accompanying drawing content are made, or directly or indirectly it is used in other related skills
Art field, is included within the scope of the present invention.
Claims (6)
1. a kind of processing method of automobile fish eye lens panoramic view picture, left side, right side, headstock and the tailstock on automobile are provided with
Fish eye lens, it is characterised in that including step：
Step S10, obtain the uncalibrated image with scaling board that fish eye lens photographs；
Step S20, Taylor polynomial model function is built based on the uncalibrated image, to calculate fish-eye inside and outside parameter；
Step S30, it is based on the inside and outside parameter that coordinate system residing for each demarcation version of automobile surrounding is unified into vehicle body coordinate system,
And the realtime graphic for shooting fish eye lens is synthesized to form auto-panorama image.
2. the processing method of automobile fish eye lens panoramic view picture as claimed in claim 1, it is characterised in that before step S10
Including step：
Step S1, four demarcation versions are placed respectively in the predeterminated position of peripheral vehicle.
3. the processing method of automobile fish eye lens panoramic view picture as claimed in claim 1, it is characterised in that the inside and outside parameter bag
Inner parameter and external parameter are included, the external parameter includes affine transformation matrix A and motion vector t, and inner parameter includes Thailand
Strangle expansion multinomial coefficient a0、a2... and aN。
4. the processing method of automobile fish eye lens panoramic view picture as claimed in claim 3, it is characterised in that the step S20 bags
Include step：
Step S21, extract the distortion point coordinate information on uncalibrated image；
Step S22, the Taylor polynomial model functional minimum value is minimized according to distortion point coordinate information, in solving
Portion's parameter and external parameter.
5. the processing method of automobile fish eye lens panoramic view picture as claimed in claim 1, it is characterised in that the demarcation version is just
Square plate, include black block and white blocks on square plate, every piece of black block or every piece of white blocks are not identical with its own color
Color lump be in contact.
6. the processing method of automobile fish eye lens panoramic view picture as claimed in claim 3, it is characterised in that the step S30 bags
Include step：
Step S31, based on the affine transformation matrix A by coordinate system direction corresponding to each demarcation version of automobile surrounding with demarcating
Version coordinate system direction is identical；
Step S32, based on the motion vector t by coordinate origin and automobile corresponding to each demarcation version of the automobile surrounding
Coordinate origin overlaps；
Step S33, the realtime graphic taken by each fish eye lens on automobile is spliced, it is complete to form complete automobile
Scape image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710632300.5A CN107492125A (en) | 2017-07-28 | 2017-07-28 | The processing method of automobile fish eye lens panoramic view picture |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710632300.5A CN107492125A (en) | 2017-07-28 | 2017-07-28 | The processing method of automobile fish eye lens panoramic view picture |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107492125A true CN107492125A (en) | 2017-12-19 |
Family
ID=60644923
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710632300.5A Pending CN107492125A (en) | 2017-07-28 | 2017-07-28 | The processing method of automobile fish eye lens panoramic view picture |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107492125A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108550106A (en) * | 2018-03-30 | 2018-09-18 | 深圳岚锋创视网络科技有限公司 | A kind of color calibration method of panoramic picture, device and electronic equipment |
| CN109461126A (en) * | 2018-10-16 | 2019-03-12 | 重庆金山医疗器械有限公司 | A kind of image distortion correction method and system |
| CN109754363A (en) * | 2018-12-26 | 2019-05-14 | 斑马网络技术有限公司 | Image composition method and device are looked around based on fisheye camera |
| CN109919941A (en) * | 2019-03-29 | 2019-06-21 | 深圳市奥特立德自动化技术有限公司 | Internal screw thread defect inspection method, device, system, equipment and medium |
| CN110689506A (en) * | 2019-08-23 | 2020-01-14 | 深圳市智顺捷科技有限公司 | Panoramic stitching method, automotive panoramic stitching method and panoramic system thereof |
| CN110895825A (en) * | 2019-11-05 | 2020-03-20 | 房春江 | Missing data detection system and method |
| CN110956585A (en) * | 2019-11-29 | 2020-04-03 | 深圳市英博超算科技有限公司 | Panoramic image splicing method and device and computer readable storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103136720A (en) * | 2013-03-12 | 2013-06-05 | 中科院微电子研究所昆山分所 | Vehicle-mounted 360-degree panorama mosaic method |
| CN103617606A (en) * | 2013-11-26 | 2014-03-05 | 中科院微电子研究所昆山分所 | Vehicle multi-angle panorama generating method for aided driving |
| CN103879352A (en) * | 2012-12-22 | 2014-06-25 | 鸿富锦精密工业（深圳）有限公司 | Car parking assistant system and car parking assistant method |
| CN103950410A (en) * | 2014-04-29 | 2014-07-30 | 深圳前向启创数码技术有限公司 | Panoramic auxiliary driving method and system |
| US8798451B1 (en) * | 2013-06-15 | 2014-08-05 | Gyeongil Kweon | Methods of obtaining panoramic images using rotationally symmetric wide-angle lenses and devices thereof |
| 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 |
| CN105825475A (en) * | 2016-04-01 | 2016-08-03 | 西安电子科技大学 | 360-degree panorama image generation method based on single pick-up head |
| CN106855999A (en) * | 2015-12-09 | 2017-06-16 | 宁波芯路通讯科技有限公司 | The generation method and device of automobile panoramic view picture |
| CN106875339A (en) * | 2017-02-22 | 2017-06-20 | 长沙全度影像科技有限公司 | A kind of fish eye images joining method based on strip scaling board |
| CN106952311A (en) * | 2017-03-02 | 2017-07-14 | 山东省科学院自动化研究所 | Auxiliary parking system and method based on panoramic mosaic data mapping tables |
-
2017
- 2017-07-28 CN CN201710632300.5A patent/CN107492125A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103879352A (en) * | 2012-12-22 | 2014-06-25 | 鸿富锦精密工业（深圳）有限公司 | Car parking assistant system and car parking assistant method |
| CN103136720A (en) * | 2013-03-12 | 2013-06-05 | 中科院微电子研究所昆山分所 | Vehicle-mounted 360-degree panorama mosaic method |
| US8798451B1 (en) * | 2013-06-15 | 2014-08-05 | Gyeongil Kweon | Methods of obtaining panoramic images using rotationally symmetric wide-angle lenses and devices thereof |
| CN103617606A (en) * | 2013-11-26 | 2014-03-05 | 中科院微电子研究所昆山分所 | Vehicle multi-angle panorama generating method for aided driving |
| CN103950410A (en) * | 2014-04-29 | 2014-07-30 | 深圳前向启创数码技术有限公司 | Panoramic auxiliary driving 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 |
| CN106855999A (en) * | 2015-12-09 | 2017-06-16 | 宁波芯路通讯科技有限公司 | The generation method and device of automobile panoramic view picture |
| CN105825475A (en) * | 2016-04-01 | 2016-08-03 | 西安电子科技大学 | 360-degree panorama image generation method based on single pick-up head |
| CN106875339A (en) * | 2017-02-22 | 2017-06-20 | 长沙全度影像科技有限公司 | A kind of fish eye images joining method based on strip scaling board |
| CN106952311A (en) * | 2017-03-02 | 2017-07-14 | 山东省科学院自动化研究所 | Auxiliary parking system and method based on panoramic mosaic data mapping tables |
Non-Patent Citations (1)
| Title |
|---|
| DAVIDE SCARAMUZZA 等: "A Toolbox for Easily Calibrating Omnidirectional Cameras", 《2006 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108550106A (en) * | 2018-03-30 | 2018-09-18 | 深圳岚锋创视网络科技有限公司 | A kind of color calibration method of panoramic picture, device and electronic equipment |
| CN108550106B (en) * | 2018-03-30 | 2021-06-01 | 影石创新科技股份有限公司 | Color correction method and device for panoramic image and electronic equipment |
| US11948228B2 (en) | 2018-03-30 | 2024-04-02 | Arashi Vision Inc. | Color correction method for panoramic image and electronic device |
| CN109461126A (en) * | 2018-10-16 | 2019-03-12 | 重庆金山医疗器械有限公司 | A kind of image distortion correction method and system |
| CN109754363A (en) * | 2018-12-26 | 2019-05-14 | 斑马网络技术有限公司 | Image composition method and device are looked around based on fisheye camera |
| CN109754363B (en) * | 2018-12-26 | 2023-08-15 | 斑马网络技术有限公司 | Around-the-eye image synthesis method and device based on fish eye camera |
| CN109919941A (en) * | 2019-03-29 | 2019-06-21 | 深圳市奥特立德自动化技术有限公司 | Internal screw thread defect inspection method, device, system, equipment and medium |
| CN110689506A (en) * | 2019-08-23 | 2020-01-14 | 深圳市智顺捷科技有限公司 | Panoramic stitching method, automotive panoramic stitching method and panoramic system thereof |
| CN110895825A (en) * | 2019-11-05 | 2020-03-20 | 房春江 | Missing data detection system and method |
| CN110956585A (en) * | 2019-11-29 | 2020-04-03 | 深圳市英博超算科技有限公司 | Panoramic image splicing method and device and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107492125A (en) | The processing method of automobile fish eye lens panoramic view picture | |
| CN103617606B (en) | For assisting the vehicle multi-angle panorama generation method of driving | |
| CN111223038B (en) | Automatic splicing method of vehicle-mounted looking-around images and display device | |
| US9858639B2 (en) | Imaging surface modeling for camera modeling and virtual view synthesis | |
| WO2021120407A1 (en) | Parallax image stitching and visualization method based on multiple pairs of binocular cameras | |
| CN108257183B (en) | Camera lens optical axis calibration method and device | |
| CN110351494B (en) | Panoramic video synthesis method and device and electronic equipment | |
| CN109948398B (en) | Image processing method for panoramic parking and panoramic parking device | |
| JP5455124B2 (en) | Camera posture parameter estimation device | |
| JP5739584B2 (en) | 3D image synthesizing apparatus and method for visualizing vehicle periphery | |
| CN102096923B (en) | Fisheye calibration method and device | |
| CN112224132B (en) | Vehicle panoramic all-around obstacle early warning method | |
| CN106875339A (en) | A kind of fish eye images joining method based on strip scaling board | |
| KR100914211B1 (en) | Distorted image correction apparatus and method | |
| CN110288527B (en) | Panoramic aerial view generation method of vehicle-mounted panoramic camera | |
| JP2008187564A (en) | Camera calibration apparatus and method, and vehicle | |
| CN103136720A (en) | Vehicle-mounted 360-degree panorama mosaic method | |
| CN112070886B (en) | Image monitoring method and related equipment for mining dump truck | |
| CN107993264A (en) | A kind of automobile looks around the scaling method of panorama | |
| CN103295231A (en) | Method for geometrically correcting vertically mapped images of fisheye lenses in fisheye image mosaic | |
| CN105488766A (en) | Fish-eye lens image correcting method and device | |
| CN111435540A (en) | Annular view splicing method of vehicle-mounted annular view system | |
| CN113034616A (en) | Camera external reference calibration method and system for vehicle all-round looking system and all-round looking system | |
| CN115936995A (en) | Panoramic splicing method for four-way fisheye cameras of vehicle | |
| CN113658262A (en) | Camera external parameter calibration method, device, system and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171219 |
|
| RJ01 | Rejection of invention patent application after publication |