CN110298788A - A kind of full-view image joining method and system based on vehicle-mounted fisheye camera - Google Patents
A kind of full-view image joining method and system based on vehicle-mounted fisheye camera Download PDFInfo
- Publication number
- CN110298788A CN110298788A CN201910404815.9A CN201910404815A CN110298788A CN 110298788 A CN110298788 A CN 110298788A CN 201910404815 A CN201910404815 A CN 201910404815A CN 110298788 A CN110298788 A CN 110298788A
- Authority
- CN
- China
- Prior art keywords
- coordinate
- camera
- full
- view image
- panorama
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 230000009466 transformation Effects 0.000 claims description 7
- 238000012937 correction Methods 0.000 claims description 6
- 229910017435 S2 In Inorganic materials 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 6
- 230000008901 benefit Effects 0.000 abstract description 4
- 230000000694 effects Effects 0.000 description 6
- 238000003384 imaging method Methods 0.000 description 6
- 241000251468 Actinopterygii Species 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Remote Sensing (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Image Processing (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention discloses a kind of full-view image joining methods and system based on vehicle-mounted fisheye camera, first resolve the corresponding panorama spherical coordinate P of coordinate of the picture point P in panoramic pixel coordinates system pixel-by-pixelO, then calculate the panorama spherical coordinate POCorresponding camera plane coordinate PC, then calculate the camera plane coordinate PCCorresponding original flake image coordinate PF, finally acquire the original flake image coordinate PFGray value, and the gray scale for the pixel element P gray value being respectively correspondingly assigned on full-view image, to obtain full-view image.The splicing of panoramic picture is carried out using the present invention, full-view image picture is clear, image quality significantly improves, and based on this technology, will significantly improve the user experience of streetscape map, bring bigger economic benefit for data manufacturer.
Description
Technical field
The present invention relates to photogrammetry technical fields, are suitable for vehicle-mounted multiple views combined type flake more particularly to one kind
The full-view image joining method and system of camera.
Background technique
With the rapid development of GIS technology, computer technology, network communication technology, networked question-answer system is by traditional
Single two-dimension vector map development is the new model of three-dimensional live map.Streetscape map is as a kind of completely new live-action map clothes
Business mode can provide 360 degree of full-view images of city, street or other environment with it for user, bring to user on the spot in person
Impression, and the favor for more the Internet enterprises and map manufacturer such as obtain Baidu, Google, Tencent falls over each other to seize this market.
It is combined currently, the acquisition equipment of streetscape map mainly passes through more cameras, shooting obtains different angle respectively
Under image, then by splicing, fusion, obtain 360 ° of full-view images.The number of cameras of the acquisition system is with separate unit
The visual angle of camera increases and reduces, and fish eye lens possesses the super large visual angle close to 180 °, can be greatly decreased needed for acquisition system
The camera quantity of carrying, reduce system cost, improve data-handling efficiency, therefore based on vehicular platform to more fisheye cameras into
Row is integrated, becomes the major way of current streetscape map data acquisition.However, being limited by special optical system and imaging mould
The image of formula, fisheye camera acquisition is often accompanied by serious metamorphopsic distortion, how to be corrected, splices to fish eye images, obtains
Full-view image data are taken, the big problem for perplexing each big data production business men is become.
Traditional image joint technology, mainly on the basis of carrying out distortion rectification to image, based between each image
Relative position and posture relationship carry out re-projection, obtain spliced a wide range of image.This method describe from raw video by
The process for corresponding to picpointed coordinate after pixel solution splicing on image, has many advantages, such as that solution procedure is simple, mathematical model is intuitive, claims
For " direct method " image joint.
However, image captured by fisheye camera is often with image very serious due to using non-linear camera lens
Distortion and deformation, are corrected using Conventional distortion and re-projection method are spliced, and " blank " will occur in the pixel caused element
(no original picture point of correspondence), and the problem of some pixel elements are likely to occur repetition (corresponding multiple original picture points), directly result in institute
It obtains full-view image and there is a large amount of " black holes ".
Summary of the invention
In view of the above-mentioned problems, this patent deduces the full-view image split-join model based on fisheye camera, using indirect
Method carries out full-view image splicing, i.e., picpointed coordinate after splicing on full-view image pixel-by-pixel reverse its on raw video
Corresponding picpointed coordinate, and gray scale interpositioning is combined, solve full-view image caused by being spliced based on " direct method " image
" black hole " problem.
Wherein one side according to the present invention, the technical solution adopted by the present invention to solve the technical problems is: construction one
Full-view image joining method of the kind based on vehicle-mounted fisheye camera, includes the following steps:
The corresponding panorama spherical coordinate P of coordinate of S1, pixel-by-pixel the picture point P in resolving panoramic pixel coordinates systemO;
S2, the panorama spherical coordinate P is calculatedOCorresponding camera plane coordinate PC;
S3, the camera plane coordinate P is calculatedCCorresponding original flake image coordinate PF;
S4, the original flake image coordinate P is acquiredFGray value, and the gray value is respectively correspondingly assigned to
The gray scale of pixel element P on full-view image, to obtain full-view image.
Further, in the full-view image joining method of the invention based on vehicle-mounted fisheye camera, in step S1, to complete
Any point P (dstx, dsty) that scape image coordinate is fastened, the respective coordinates P on panorama ballOBy point on spherical surface with
The angle of X-axisIt is converted to the angle theta of XOY plane, transformational relation is as follows:
In formula, imgW, imgH respectively indicate full-view image width and height.
Further, in the full-view image joining method of the invention based on vehicle-mounted fisheye camera, in step S2, panorama
Coordinate on spherical surfaceWith camera plane coordinate PCTransformation relation is calculated according to following formula between (u, v):
In formula, (XC,YC,ZC) it is the coordinate of the single camera that is obtained in advance by calibration under panorama spherical coordinate system, a1、
a2、a3、b1、b2、b3、c1、c2、c3Rotating vector value of the single camera i obtained for calibration in panorama spherical coordinate system, f indicate inspection
The single camera master that school obtains away from, and:
ZG=ZO+D*sinθ;
In formula, (XO,YO,ZO) it is panorama ball center coordinate, D is object space distance.
Further, in the full-view image joining method of the invention based on vehicle-mounted fisheye camera, step S3 is specifically wrapped
It includes:
S31, it is obtained to diameter value according to camera plane coordinate valueAnd it cuts angle
S32, the acquisition data according to S31 have carried out multinomial to the inverse function of the general distortion correction model of fisheye camera
Fitting, obtains camera plane coordinate to diameter size rCWith fisheye camera spherical coordinate to diameter size rFCorresponding relationship;Wherein, intend
Close obtained multinomial are as follows:
rF=p1rC n+p2rC n-1+…+pnrC+pn+1;
In formula, p1,p2,…,pn+1To carry out the multinomial coefficient that inverse function is fitted to distortion function obtained by calibration;Phase
Machine plane coordinates is to diameter size rCWith fisheye camera spherical coordinate to diameter size rFCorresponding relationship are as follows:
xF=rFcosα;
yF=rF sinα。
According to another aspect of the present invention, the present invention is to solve its technical problem, is additionally provided a kind of based on vehicle-mounted flake
The full-view image splicing system of camera, including such as lower unit:
Panorama spherical coordinate transformation unit, the coordinate pair for resolving the picture point P in panoramic pixel coordinates system pixel-by-pixel are answered
Panorama spherical coordinate PO;
Camera plane coordinate transformation unit, for calculating the panorama spherical coordinate POCorresponding camera plane coordinate PC;
Flake image coordinate converting unit, for calculating the camera plane coordinate PCCorresponding original flake image coordinate
PF;
Gray scale interpolation and assignment unit, for acquiring the original flake image coordinate PFGray value, and by the ash
Angle value is respectively correspondingly assigned to the gray scale of the pixel element P on full-view image, to obtain full-view image.
Further, in the full-view image splicing system of the invention based on vehicle-mounted fisheye camera, panorama spherical coordinate
Respective coordinates P in converting unit, to any point P (dstx, dsty) on full-view image coordinate system, on panorama ballO
Pass through the angle of the point on spherical surface and X-axisIt is converted to the angle theta of XOY plane, transformational relation is as follows:
In formula, imgW, imgH respectively indicate full-view image width and height.
Further, in the full-view image splicing system of the invention based on vehicle-mounted fisheye camera, camera plane coordinate
In converting unit, coordinate on panorama spherical surfaceWith camera plane coordinate PCTransformation relation is according to following public affairs between (u, v)
Formula is calculated:
In formula, (XC,YC,ZC) it is the coordinate of the single camera that is obtained in advance by calibration under panorama spherical coordinate system, a1、
a2、a3、b1、b2、b3、c1、c2、c3Rotating vector value of the single camera obtained for calibration in panorama spherical coordinate system, f indicate inspection
The single camera master that school obtains away from, and:
ZG=ZO+D*sinθ;
In formula, (XO,YO,ZO) it is panorama ball center coordinate, D is object space distance.
Further, in the full-view image splicing system of the invention based on vehicle-mounted fisheye camera, flake image coordinate
Converting unit specifically includes:
First subelement, for obtaining it to diameter value according to camera plane coordinate valueAnd it cuts angle
Second subelement, for the acquisition data according to the first subelement, to the general distortion correction model of fisheye camera
Inverse function has carried out fitting of a polynomial, obtains camera plane coordinate to diameter size rCWith fisheye camera spherical coordinate to diameter size rF
Corresponding relationship;Wherein, the multinomial being fitted are as follows:
rF=p1rC n+p2rC n-1+…+pnrC+pn+1;
In formula, p1,p2,…,pn+1To carry out the multinomial coefficient that inverse function is fitted to distortion function obtained by calibration;Phase
Machine plane coordinates is to diameter size rCWith fisheye camera spherical coordinate to diameter size rFCorresponding relationship are as follows:
xF=rFcosα;
yF=rF sinα。
Implement in the full-view image joining method and system of the invention based on vehicle-mounted fisheye camera, have beneficial below
Effect: the splicing of panoramic picture is carried out using the present invention, full-view image picture is clear, image quality significantly improves, with this skill
Based on art, the user experience of streetscape map will be significantly improved, bring bigger economic benefit for data manufacturer.
Detailed description of the invention
Present invention will be further explained below with reference to the attached drawings and examples, in attached drawing:
Fig. 1 is that traditional direct method splicing leads to a large amount of black holes effect picture present on full-view image;
Fig. 2 is the flow chart of one embodiment of full-view image joining method based on vehicle-mounted fisheye camera;
Fig. 3 is transition diagram of the panoramic pixel coordinates system to panorama spheric coordinate system;
Fig. 4 is transition diagram of the panorama spheric coordinate system to single camera plane coordinate system;
Fig. 5 is the panorama camera structural map of current mainstream on the market;
Fig. 6 is indirect method full-view image splicing effect figure.
Specific embodiment
For a clearer understanding of the technical characteristics, objects and effects of the present invention, now control attached drawing is described in detail
A specific embodiment of the invention.
Currently, streetscape map acquisition is main with respect to factors such as the continuity of map, imaging viewing field angle, image resolutions
It is to be obtained by vehicle-mounted multiple views combined type flake panorama camera.Since data volume is big, the imaging pattern that fisheye camera is special etc.
The influence of aspect factor, traditional direct method splicing will lead to gained full-view image image blur and existing a large amount of " black holes "
Problem greatly affected the experience of streetscape map user.
Towards based on vehicle-mounted fisheye camera full-view image splice demand, this patent data are acquired, distortion correction, as
The processes such as point projection and gray scale assignment carry out on the basis of combing in detail, have carried out reverse deduction to full-view image imaging process,
A kind of indirect full-view image joining method is proposed, i.e., from target full-view image, in conjunction with opposite between distortion correction, camera
The parameters such as position and posture relationship resolve its corresponding raw video pixel coordinate pixel-by-pixel, and combine gray scale interpositioning, obtain
Each picture point gray value on target full-view image, ultimately generate 360 ° of full-view images, thus for improve full-view image image quality,
Improve streetscape map user experience to lay the foundation.
With reference to Fig. 2, image joint of the invention is related to solving its corresponding original flake shadow from full-view image pixel coordinate
As upper pixel coordinate and multiple processes such as carry out gray scale assignment, the following steps progress is specifically included:
S1, the pixel-by-pixel corresponding panorama spherical coordinate P of picture point P in resolving panoramic pixel coordinates systemO
Panoramic pixel coordinates system is as shown in Figure 3 to the projection relation between panorama spheric coordinate system.To appointing on full-view image
Anticipate a point P (dstx, dsty), the respective coordinates P on panorama ballOThe angle of the point on spherical surface and X-axis can be passed throughWith
The angle theta of XOY plane indicates that transformational relation is as follows:
In formula, imgW, imgH respectively indicate full-view image width and height.
S2, panorama spherical coordinate P is calculatedOCorresponding single camera plane coordinates PC
By flake image distortion and deformation large effect, picture point is being obtained after the coordinate in panorama spheric coordinate system,
It can not directly be corresponded in the coordinate system of single fisheye camera, and need first to be translated into ideal plane coordinates
System.Panorama spheric coordinate system is as shown in Figure 4 to the transformation relation between single camera plane coordinate system:
Due to panorama sphere centre O and each camera shooting center C and it is non-critical be located at same geometric center, solving
Calculate coordinate on panorama spherical surfaceWith camera plane coordinate PCBetween (u, v) when transformation relation, often first take hypothesis a certain
Object space distance D resolves the corresponding object space point P of umbilical pointGCoordinate value:
ZG=ZO+D*sinθ
In formula, (XO,YO,ZO) it is panorama ball center coordinate, since panorama spheric coordinate system is often using the center as origin,
The coordinate is generally (0,0,0);
Then, according to POSpecific location on panorama ball, in conjunction with the field angle size of each single camera and its in panorama
Direction in imaging system calculates POCorresponding single camera number i recycles collinearity condition equation to solve the point flat in camera
Coordinate value (u, v) in areal coordinate system:
In formula, (XC,YC,ZC) it is seat of the prior single camera i obtained by high-precision calibration under panorama spherical coordinate system
Mark;F be the obtained master of camera i of calibration away from.a1,a2,…,c3Rotation of the camera i obtained for calibration in panorama spherical coordinate system
Vector.
S3, camera plane coordinate P is calculatedCCorresponding original flake image coordinate PF
It, can be according to fisheye camera spherical coordinate under the premise of prior high-precision calibration obtains the distortion factor of fisheye camera
Resolve its corresponding camera plane coordinate, but after switching to plane from spherical surface due to image, image size is significantly stretched, therefore,
Often there is a large amount of " black holes " using the flat image that the method obtains.To make up this deficiency, this patent is first according to camera
Plane coordinate value obtains it to diameter valueAnd it cuts angleAgain to the general distortion school of fisheye camera
The inverse function of positive model has carried out fitting of a polynomial, obtains camera plane coordinate to diameter size rCWith fisheye camera spherical coordinate to
Diameter size rFCorresponding relationship:
rF=p1rC n+p2rC n-1+…+pnrC+pn+1
In formula, p1,p2,…,pn+1To carry out the multinomial coefficient that inverse function is fitted to distortion function obtained by calibration;
Then, the coordinate value under its corresponding original flake coordinate systems in image is resolved:
xF=rFcosα
yF=rF sinα
S4, gray scale interpolation and assignment
After the calculating of above three step, the corresponding original flake of each picture point on target full-view image can be obtained
Picpointed coordinate value on image, but since obtained picpointed coordinate is not necessarily just fallen in as element center, it is therefore desirable into
Row gray scale interpolation, generally can be used bilinear interpolation method, acquire picture point PFGray value g (xF,yF), and respectively corresponded
Ground is assigned to the gray scale G (dstx, dsty) of the pixel element P on full-view image:
G (dstx, dsty)=g (xF,yF)
After the above coordinate transform, gray scale interpolation and assignment, spliced full-view image can be obtained.
By at present on the market for the panorama camera of mainstream 5+1 construction (5 fisheye cameras round horizontal setting, 1
Upward for shooting zenith direction image, as shown in Figure 5), the indirect method for carrying out data acquisition, and being proposed based on this patent into
The splicing of row full-view image, effect are as shown in Figure 6.
It is compared by Fig. 1 and Fig. 6, it can be seen that spliced using direct method, obtained full-view image imaging
It is fuzzy and there is a large amount of " black holes ", and it is of the invention spliced based on indirect method, then effectively evaded this problem, entirely
Scape image frame is clear, image quality significantly improves, and based on this technology, will significantly improve the user's body of streetscape map
It tests, bring bigger economic benefit for data manufacturer.
The embodiment of the present invention is described with above attached drawing, but the invention is not limited to above-mentioned specific
Embodiment, the above mentioned embodiment is only schematical, rather than restrictive, those skilled in the art
Under the inspiration of the present invention, without breaking away from the scope protected by the purposes and claims of the present invention, it can also make very much
Form, all of these belong to the protection of the present invention.
Claims (8)
1. a kind of full-view image joining method based on vehicle-mounted fisheye camera, which comprises the steps of:
The corresponding panorama spherical coordinate P of coordinate of S1, pixel-by-pixel the picture point P in resolving panoramic pixel coordinates systemO;
S2, the panorama spherical coordinate P is calculatedOCorresponding camera plane coordinate PC;
S3, the camera plane coordinate P is calculatedCCorresponding original flake image coordinate PF;
S4, the original flake image coordinate P is acquiredFGray value, and the gray value is respectively correspondingly assigned to panorama shadow
As the gray scale of upper pixel element P, to obtain full-view image.
2. the full-view image joining method according to claim 1 based on vehicle-mounted fisheye camera, which is characterized in that step S1
In, the respective coordinates P to any point P (dstx, dsty) on full-view image coordinate system, on panorama ballOPass through spherical surface
On point and X-axis angleIt is converted to the angle theta of XOY plane, transformational relation is as follows:
In formula, imgW, imgH respectively indicate full-view image width and height.
3. the full-view image joining method according to claim 2 based on vehicle-mounted fisheye camera, which is characterized in that step S2
In, coordinate on panorama spherical surfaceWith camera plane coordinate PCTransformation relation is calculated according to following formula between (u, v)
Out:
In formula, (XC,YC,ZC) it is the coordinate of the single camera that is obtained in advance by calibration under panorama spherical coordinate system, a1、a2、a3、
b1、b2、b3、c1、c2、c3Rotating vector value of the single camera obtained for calibration in panorama spherical coordinate system, f indicate that calibration obtains
Single camera master away from, and:
ZG=ZO+D*sinθ;
In formula, (XO,YO,ZO) it is panorama ball center coordinate, D is object space distance.
4. the full-view image joining method according to claim 3 based on vehicle-mounted fisheye camera, which is characterized in that step S3
It specifically includes:
S31, it is obtained to diameter value according to camera plane coordinate valueAnd it cuts angle
S32, the acquisition data according to S31 have carried out fitting of a polynomial to the inverse function of the general distortion correction model of fisheye camera,
Camera plane coordinate is obtained to diameter size rCWith fisheye camera spherical coordinate to diameter size rFCorresponding relationship;Wherein, fitting obtains
Multinomial are as follows:
rF=p1rC n+p2rC n-1+…+pnrC+pn+1;
In formula, p1,p2,…,pn+1To carry out the multinomial coefficient that inverse function is fitted to distortion function obtained by calibration;Camera is flat
Areal coordinate is to diameter size rCWith fisheye camera spherical coordinate to diameter size rFCorresponding relationship are as follows:
xF=rFcosα;
yF=rFsinα。
5. a kind of full-view image splicing system based on vehicle-mounted fisheye camera, which is characterized in that including such as lower unit:
Panorama spherical coordinate transformation unit, the coordinate for resolving the picture point P in panoramic pixel coordinates system pixel-by-pixel are corresponding complete
Scape spherical coordinate PO;
Camera plane coordinate transformation unit, for calculating the panorama spherical coordinate POCorresponding camera plane coordinate PC;
Flake image coordinate converting unit, for calculating the camera plane coordinate PCCorresponding original flake image coordinate PF;
Gray scale interpolation and assignment unit, for acquiring the original flake image coordinate PFGray value, and by the gray value point
The gray scale of the pixel element P on full-view image is not assigned to accordingly, to obtain full-view image.
6. the full-view image splicing system according to claim 5 based on vehicle-mounted fisheye camera, which is characterized in that panorama ball
Correspondence in areal coordinate converting unit, to any point P (dstx, dsty) on full-view image coordinate system, on panorama ball
Coordinate POPass through the angle of the point on spherical surface and X-axisIt is converted to the angle theta of XOY plane, transformational relation is as follows:
In formula, imgW, imgH respectively indicate full-view image width and height.
7. the full-view image splicing system according to claim 6 based on vehicle-mounted fisheye camera, which is characterized in that camera is flat
In areal coordinate converting unit, coordinate on panorama spherical surfaceWith camera plane coordinate PCTransformation relation is basis between (u, v)
Following formula are calculated:
In formula, (XC,YC,ZC) it is the coordinate of the single camera that is obtained in advance by calibration under panorama spherical coordinate system, a1、a2、a3、
b1、b2、b3、c1、c2、c3Rotating vector value of the single camera obtained for calibration in panorama spherical coordinate system, f indicate that calibration obtains
Single camera master away from, and:
ZG=ZO+D*sinθ;
In formula, (XO,YO,ZO) it is panorama ball center coordinate, D is object space distance.
8. the full-view image splicing system according to claim 7 based on vehicle-mounted fisheye camera, which is characterized in that flake shadow
As coordinate transformation unit specifically includes:
First subelement, for obtaining it to diameter value according to camera plane coordinate valueAnd it cuts angle
Second subelement, for the acquisition data according to the first subelement, to the anti-letter of the general distortion correction model of fisheye camera
Number has carried out fitting of a polynomial, obtains camera plane coordinate to diameter size rCWith fisheye camera spherical coordinate to diameter size rFPair
It should be related to;Wherein, the multinomial being fitted are as follows:
rF=p1rC n+p2rC n-1+…+pnrC+pn+1;
In formula, p1,p2,…,pn+1To carry out the multinomial coefficient that inverse function is fitted to distortion function obtained by calibration;Camera is flat
Areal coordinate is to diameter size rCWith fisheye camera spherical coordinate to diameter size rFCorresponding relationship are as follows:
xF=rFcosα;
yF=rFsinα。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910404815.9A CN110298788A (en) | 2019-05-16 | 2019-05-16 | A kind of full-view image joining method and system based on vehicle-mounted fisheye camera |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910404815.9A CN110298788A (en) | 2019-05-16 | 2019-05-16 | A kind of full-view image joining method and system based on vehicle-mounted fisheye camera |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110298788A true CN110298788A (en) | 2019-10-01 |
Family
ID=68026844
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910404815.9A Withdrawn CN110298788A (en) | 2019-05-16 | 2019-05-16 | A kind of full-view image joining method and system based on vehicle-mounted fisheye camera |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110298788A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117422650A (en) * | 2023-12-18 | 2024-01-19 | 湖北珞珈实验室 | Panoramic image distortion correction method and device, electronic equipment and medium |
-
2019
- 2019-05-16 CN CN201910404815.9A patent/CN110298788A/en not_active Withdrawn
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117422650A (en) * | 2023-12-18 | 2024-01-19 | 湖北珞珈实验室 | Panoramic image distortion correction method and device, electronic equipment and medium |
CN117422650B (en) * | 2023-12-18 | 2024-03-08 | 湖北珞珈实验室 | Panoramic image distortion correction method and device, electronic equipment and medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106875339B (en) | Fisheye image splicing method based on strip-shaped calibration plate | |
CN110197466B (en) | Wide-angle fisheye image correction method | |
TWI622021B (en) | Method and apparatus for generating panoramic image with stitching process | |
CN109903227B (en) | Panoramic image splicing method based on camera geometric position relation | |
CN108122191B (en) | Method and device for splicing fisheye images into panoramic image and panoramic video | |
CN110782394A (en) | Panoramic video rapid splicing method and system | |
CN111243033B (en) | Method for optimizing external parameters of binocular camera | |
CN112085659B (en) | Panorama splicing and fusing method and system based on dome camera and storage medium | |
CN106651808B (en) | Fisheye diagram conversion method and device | |
KR100914211B1 (en) | Distorted image correction apparatus and method | |
CN111199528A (en) | Fisheye image distortion correction method | |
CN111784585B (en) | Image splicing method and device, electronic equipment and computer readable storage medium | |
CN105023260A (en) | Panorama image fusion method and fusion apparatus | |
CN108200360A (en) | A kind of real-time video joining method of more fish eye lens panoramic cameras | |
CN105825470A (en) | Fisheye image correction method base on point cloud image | |
CN111009030A (en) | Multi-view high-resolution texture image and binocular three-dimensional point cloud mapping method | |
CN108269234B (en) | Panoramic camera lens attitude estimation method and panoramic camera | |
KR100614004B1 (en) | An automated method for creating 360 degrees panoramic image | |
CN108898550B (en) | Image splicing method based on space triangular patch fitting | |
CN114331835A (en) | Panoramic image splicing method and device based on optimal mapping matrix | |
CN110428361A (en) | A kind of multiplex image acquisition method based on artificial intelligence | |
CN110298788A (en) | A kind of full-view image joining method and system based on vehicle-mounted fisheye camera | |
CN112258581A (en) | On-site calibration method for multi-fish glasses head panoramic camera | |
CN110958444A (en) | 720-degree view field environment situation sensing method and situation sensing system | |
CN113689339B (en) | Image stitching method and device |
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 | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20191001 |