CN107133912A - Panoramic parking image distortion correction method and device - Google Patents
Panoramic parking image distortion correction method and device Download PDFInfo
- Publication number
- CN107133912A CN107133912A CN201710213788.8A CN201710213788A CN107133912A CN 107133912 A CN107133912 A CN 107133912A CN 201710213788 A CN201710213788 A CN 201710213788A CN 107133912 A CN107133912 A CN 107133912A
- Authority
- CN
- China
- Prior art keywords
- image
- projection
- virtual cylinder
- distortion correction
- picture
- 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
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000012937 correction Methods 0.000 title claims abstract description 25
- 230000000007 visual effect Effects 0.000 abstract description 6
- 230000033001 locomotion Effects 0.000 description 16
- 238000005516 engineering process Methods 0.000 description 11
- 230000009466 transformation Effects 0.000 description 10
- 230000008859 change Effects 0.000 description 8
- 230000004927 fusion Effects 0.000 description 6
- 238000013519 translation Methods 0.000 description 6
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000000875 corresponding effect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000002156 mixing Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 230000003138 coordinated effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
Classifications
-
- G06T3/08—
-
- G06T3/047—
-
- G06T3/053—
-
- 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
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
- G06T7/344—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods involving models
Abstract
Panoramic parking image distortion correction method and device that the present invention is provided, by under physical coordinates system, setting up a virtual cylinder centered on the image collecting device located at the wide-angle of vehicle body, wherein, the central axis direction of the virtual cylinder is variable;Using nominal data, image collecting device is gathered picture back projection to the virtual cylinder to form re-projection image;Re-projection image on the virtual cylinder is cut into output;The Severe distortion on picture is not only eliminated, enough original image informations are remained again, also, output image is a more flexible variable visual angle unrelated with video camera setting angle so that picture is more directly perceived.
Description
Technical field
The present invention relates to panoramic picture generation technique field, more particularly to panoramic parking image distortion correction method and dress
Put.
Background technology
With the fast development of image and computer vision technique, increasing technology is applied to automotive electronics neck
Domain, traditional reverse image system based on image only installs camera in the tailstock, can only cover region limited around the tailstock,
And the blind area of vehicle periphery and headstock undoubtedly adds the hidden danger of safe driving, easily go out in the urban district and parking lot of narrow congestion
Now collide and scratch event.To expand driver's seat, it just must be able to perceive 360 ° of comprehensive environment, this is accomplished by multiple regard
Feel the mutual coordinated effect of sensor and then handled by Video Composition, a whole set of the video figure formed around full car
Picture, is exactly this kind of demand, and Full view vision parking assisting system arises at the historic moment.
But, because panorama parks camera for ultra wide-angle imaging head (such as fish-eye camera), compared to general camera figure
As there is larger distortion, picture is not directly perceived enough.
In the prior art, two kinds of processing typically eliminate the mode of distortion:
1st, the middle position subregion image of original image is absorbed by choosing camera, is amplified to and requires chi
Very little output processing;So, such a image procossing mode, image is stretched because of amplification, has certain fuzzy problem, in addition because of an output section
Divide original image, raw frames information has certain abandon to lose.
2nd, area's distortion is carried out by the original image for being absorbed camera and is processed into common perspective projection image, taken certain
Multi-view image is exported;So, the method has middle clear and edge because stretching excessive fuzzy problem, while raw frames visual field model
Enclosing also has greater loss.
The content of the invention
The shortcoming of prior art in view of the above, it is an object of the invention to provide panoramic parking image distortion correction side
Method and device, for solving the problem of panoramic picture distorts in the prior art.
In order to achieve the above objects and other related objects, the present invention provides a kind of panoramic parking image distortion correction method,
Including:Under physical coordinates system, a virtual cylinder is set up centered on the image collecting device located at the wide-angle of vehicle body, its
In, the central axis direction of the virtual cylinder is variable;Using nominal data, image collecting device is gathered into picture back projection extremely
To form re-projection image on the virtual cylinder;Re-projection image on the virtual cylinder is cut into output.
In one embodiment of the invention, the virtual cylinder is vertically arranged, to make the re-projection image as level side
To.
In one embodiment of the invention, described image harvester is fish-eye camera.
In one embodiment of the invention, described image harvester has four, be respectively arranged on the forward and backward, left of vehicle body and
Right position.
In one embodiment of the invention, methods described also includes:Utilize each image collecting device for being correspondingly arranged at vehicle body
Obtained re-projection image generates the panoramic picture of vehicle.
In order to achieve the above objects and other related objects, the present invention provides a kind of panoramic parking image distortion correction device,
Including:Model building module, under physical coordinates system, being set up centered on the image collecting device located at the wide-angle of vehicle body
One virtual cylinder, wherein, the central axis direction of the virtual cylinder is variable;Projection module, for utilizing nominal data, by image
Harvester gathers picture back projection to the virtual cylinder to form re-projection image;Image output module, for inciting somebody to action
Re-projection image on the virtual cylinder cuts output.
In one embodiment of the invention, the virtual cylinder is vertically arranged, to make the re-projection image as level side
To.
In one embodiment of the invention, described image harvester is fish-eye camera.
In one embodiment of the invention, described image harvester has four, be respectively arranged on the forward and backward, left of vehicle body and
Right position.
In one embodiment of the invention, the panoramic parking image distortion correction device also includes:Panoramic picture is generated
Module, the panorama sketch of vehicle is generated for the re-projection image obtained using each image collecting device for being correspondingly arranged at vehicle body
Picture.
As described above, panoramic parking image distortion correction method and device that the present invention is provided, by physical coordinates system
Under, a virtual cylinder is set up centered on the image collecting device located at the wide-angle of vehicle body, wherein, in the virtual cylinder
Direction of principal axis is variable;Using nominal data, image collecting device is gathered picture back projection to the virtual cylinder to be formed
Re-projection image;Re-projection image on the virtual cylinder is cut into output;The Severe distortion on picture is not only eliminated, again
Remain enough original image informations, also, output image is one unrelated with video camera setting angle more flexible
Variable visual angle so that picture is more directly perceived.
Brief description of the drawings
Fig. 1 is shown as the schematic flow sheet of panoramic parking image distortion correction method of the present invention in an embodiment.
Fig. 2 is shown as the module diagram of panoramic parking image distortion correction device of the present invention in an embodiment.
Component label instructions
201 model building modules
202 projection modules
203 image output modules
S101~S103 method and steps
Embodiment
Illustrate embodiments of the present invention below by way of specific instantiation, those skilled in the art can be by this specification
Disclosed content understands other advantages and effect of the present invention easily.The present invention can also pass through specific realities different in addition
The mode of applying is embodied or practiced, the various details in this specification can also based on different viewpoints with application, without departing from
Various modifications or alterations are carried out under the spirit of the present invention.It should be noted that, in the case where not conflicting, following examples and implementation
Feature in example can be mutually combined.
It should be noted that the diagram provided in following examples only illustrates the basic structure of the present invention in a schematic way
Think, then in schema only display with relevant component in the present invention rather than according to component count, shape and the size during actual implement
Draw, it is actual when implementing, and kenel, quantity and the ratio of each component can be a kind of random change, and its assembly layout kenel
It is likely more complexity.
Technical scheme, is parked technical field applied to panorama, for eliminating due to being adopted using the image of wide-angle
The pattern distortion that acquisition means are produced.
In one embodiment of the invention, described image harvester is fish-eye camera;In general, described image is adopted
Acquisition means can have four, be respectively arranged on forward and backward, the left and right position of vehicle body, and the image collecting device of forward and backward position can be set
In the midline position of vehicle body, the medium position of such as bumper, and the image collecting device of the arranged on left and right sides can located at it is left,
The position of right rear view mirror.
As shown in figure 1, the present invention provides a kind of panoramic parking image distortion correction method embodiment, it includes:
Step S101:Under physical coordinates system, one is set up centered on the image collecting device located at the wide-angle of vehicle body
Virtual cylinder, wherein, the central axis direction of the virtual cylinder is variable.
In one embodiment of the invention, the virtual cylinder may be, for example, the face of cylinder;In the physical coordinates of real world
Under system, if described image harvester is located at the center of the cylinder.
Step S102:Using nominal data, image collecting device is gathered into picture back projection to the virtual cylinder
To form re-projection image.
In one embodiment of the invention, described image harvester is located at the center of the cylinder, and its collection can be absorbed
External image, and then the image be projected to again assumed on virtual cylinder outside it, re-projection is formed, so as to eliminate abnormal
Become.
Specifically, in cylinder perspective projection model, the linear projection in space is no longer straight line, but ellipse on cylinder
These points, by choosing sampled point on the original image, are mapped as the point on cylinder by circle, and utilize image collecting device demarcation
Parameter can calculate mapping between the physical coordinates of the coordinate of any on original image and the corresponding points on re-projection image is closed
System, therefore, you can the point on each original image of correspondence obtains the physical coordinates of each point on re-projection image, so as to obtain
Re-projection image.
Step S103:Re-projection image on the virtual cylinder is cut into output.
Specifically, when cylinder is designed as vertical direction, output picture is horizontal view angle, and if desired other are regarded
Angle, it is vertical with Requirement to design adjustment interarea direction, in this way, output image be one and video camera setting angle without
The more flexible variable visual angle closed so that picture is more directly perceived.
And then, the re-projection image of each image collecting device located at vehicle body is obtained using said process, splicing can be passed through
To generate the panoramic picture of vehicle, image mosaic (Image Stitching) is that one kind constitutes panoramic space using real scene image
Technology, multiple image is spliced into a width large scale image or 360 degree of panorama sketch by it, and image mosaic technology is related to computer
The technologies such as vision, computer graphics, Digital Image Processing and some mathematical tools.
Crucial two step of image mosaic is:Registering (registration) and fusion (blending).Registration purpose be
According to geometry motion model, by image registration into same coordinate system;Fusion is then that the image after registration is synthesized into one
Big stitching image.
During multiple image registration, the geometry motion model of use mainly has:Translation model, Similarity Model,
Affine model and perspective model.The translation model of image refers to that image only there occurs the displacement in direction and direction in two-dimensional space,
If video camera only there occurs translational motion, translation model can be used.The Similarity Model of image refers to video camera sheet
Body in addition to translational motion it may also happen that rotary motion, meanwhile, when there is the scaling of scene, zoom factor can also be utilized
Many scaling motions are described, therefore, may translate when image, rotate, scale when moving, can use similitude mould
Type.The affine model of image is the transformation model of 6 parameters, i.e., be transformed into parallel lines with parallel lines, and finite point is mapped to
The general characteristic of finite point, specific manifestation can be the consistent uniform scaling conversion of all directions change of scale coefficient or transformation series
Number is inconsistent non-with change of scale and shear transformation etc., can describe the contracting of translational motion, rotary motion and small range
Put and deform.The perspective model of image is the transformation model with 8 parameters, can ideally state various tables and change, and is a kind of
Precise transformation model the most.Image fusion technology generally can be divided into non-multi-level technique and the class of multi-level technique two.Non-
Mainly there are mean value method, cap function method, weighted mean method and median filtering method etc. in multi-level technique.Multi-level technique
Mainly there are gaussian pyramid, laplacian pyramid, contrast pyramid, grad pyramid and small echo etc..
As shown in Fig. 2 the present invention provides a kind of embodiment of panoramic parking image distortion correction device, its principle with it is above-mentioned
Embodiment of the method is roughly the same, therefore identical ins and outs are not repeated and repeated;Described device includes:Model building module
201st, projection module 202 and image output module 203.
The model building module 201, under physical coordinates system, with located at the image collecting device of the wide-angle of vehicle body
Centered on set up a virtual cylinder, wherein, the central axis direction of the virtual cylinder is variable.In one embodiment of the invention,
The virtual cylinder may be, for example, the face of cylinder;Under the physical coordinates system of real world, it is somebody's turn to do if described image harvester is located at
The center of cylinder.
The projection module 202, for utilizing nominal data, gathers picture back projection by image collecting device and extremely should
To form re-projection image on virtual cylinder, in one embodiment of the invention, described image harvester is located at the cylinder
Center, it gathers the external image that can be absorbed, and then the image is projected on the virtual cylinder assumed outside it again, shape
Into re-projection, so as to eliminate distortion.Specifically, in cylinder perspective projection model, the linear projection in space is no longer straight line,
But the ellipse on cylinder, by choosing sampled point on the original image, these points are mapped as with the point on cylinder, and utilize figure
As harvester calibrating parameters can calculate to obtain the coordinate of any and the physics of the corresponding points on re-projection image on original image
Mapping relations between coordinate, therefore, you can the point on each original image of correspondence obtains the thing of each point on re-projection image
Coordinate is managed, so as to obtain re-projection image.
Described image output module 203, for the re-projection image on the virtual cylinder to be cut into output.
In subsequent step, the re-projection image of each image collecting device located at vehicle body is obtained using said process, can
The panoramic picture of vehicle is generated by splicing, image mosaic (Image Stitching) is that one kind utilizes real scene image composition
The technology of panoramic space, multiple image is spliced into a width large scale image or 360 degree of panorama sketch by it, and image mosaic technology is related to
To technologies such as computer vision, computer graphics, Digital Image Processing and some mathematical tools.
Crucial two step of image mosaic is:Registering (registration) and fusion (blending).Registration purpose be
According to geometry motion model, by image registration into same coordinate system;Fusion is then that the image after registration is synthesized into one
Big stitching image.
During multiple image registration, the geometry motion model of use mainly has:Translation model, Similarity Model,
Affine model and perspective model.The translation model of image refers to that image only there occurs the displacement in direction and direction in two-dimensional space,
If video camera only there occurs translational motion, translation model can be used.The Similarity Model of image refers to video camera sheet
Body in addition to translational motion it may also happen that rotary motion, meanwhile, when there is the scaling of scene, zoom factor can also be utilized
Many scaling motions are described, therefore, may translate when image, rotate, scale when moving, can use similitude mould
Type.The affine model of image is the transformation model of 6 parameters, i.e., be transformed into parallel lines with parallel lines, and finite point is mapped to
The general characteristic of finite point, specific manifestation can be the consistent uniform scaling conversion of all directions change of scale coefficient or transformation series
Number is inconsistent non-with change of scale and shear transformation etc., can describe the contracting of translational motion, rotary motion and small range
Put and deform.The perspective model of image is the transformation model with 8 parameters, can ideally state various tables and change, and is a kind of
Precise transformation model the most.Image fusion technology generally can be divided into non-multi-level technique and the class of multi-level technique two.Non-
Mainly there are mean value method, cap function method, weighted mean method and median filtering method etc. in multi-level technique.Multi-level technique
Mainly there are gaussian pyramid, laplacian pyramid, contrast pyramid, grad pyramid and small echo etc..
Specifically, when cylinder is designed as vertical direction, output picture is horizontal view angle, and if desired other are regarded
Angle, it is vertical with Requirement to design adjustment interarea direction, in this way, output image be one and video camera setting angle without
The more flexible variable visual angle closed so that picture is more directly perceived.
In one embodiment of the invention, the virtual cylinder is vertically arranged, to make the re-projection image as level side
To.
In one embodiment of the invention, described image harvester is fish-eye camera.
In one embodiment of the invention, described image harvester has four, be respectively arranged on the forward and backward, left of vehicle body and
Right position.
In one embodiment of the invention, the panoramic parking image distortion correction device also includes:Panoramic picture is generated
Module, the panorama sketch of vehicle is generated for the re-projection image obtained using each image collecting device for being correspondingly arranged at vehicle body
Picture.
In summary, the present invention is provided panoramic parking image distortion correction method and device, by physical coordinates system
Under, a virtual cylinder is set up centered on the image collecting device located at the wide-angle of vehicle body, wherein, in the virtual cylinder
Direction of principal axis is variable;Using nominal data, image collecting device is gathered picture back projection to the virtual cylinder to be formed
Re-projection image;Re-projection image on the virtual cylinder is cut into output;The Severe distortion on picture is not only eliminated, again
Remain enough original image informations, also, output image is one unrelated with video camera setting angle more flexible
Variable visual angle so that picture is more directly perceived.
The present invention effectively overcomes various shortcoming of the prior art and has high industrial utilization.
The above-described embodiments merely illustrate the principles and effects of the present invention, not for the limitation present invention.It is any ripe
Know the personage of this technology all can carry out modifications and changes under the spirit and scope without prejudice to the present invention to above-described embodiment.Cause
This, those of ordinary skill in the art is complete without departing from disclosed spirit and institute under technological thought such as
Into all equivalent modifications or change, should by the present invention claim be covered.
Claims (10)
1. a kind of panoramic parking image distortion correction method, it is characterised in that including:
Under physical coordinates system, a virtual cylinder is set up centered on the image collecting device located at the wide-angle of vehicle body, wherein,
The central axis direction of the virtual cylinder is variable;
Using nominal data, image collecting device is gathered picture back projection to the virtual cylinder to form re-projection figure
Picture;
Re-projection image on the virtual cylinder is cut into output.
2. panoramic parking image distortion correction method according to claim 1, it is characterised in that the virtual cylinder is vertical
Set, to make the re-projection image as horizontal direction.
3. panoramic parking image distortion correction method according to claim 1, it is characterised in that described image harvester
For fish-eye camera.
4. panoramic parking image distortion correction method according to claim 1, it is characterised in that described image harvester
There are four, be respectively arranged on forward and backward, the left and right position of vehicle body.
5. panoramic parking image distortion correction method according to claim 1, it is characterised in that also include:Utilize correspondence
The re-projection image that obtains located at each image collecting device of vehicle body generates the panoramic picture of vehicle.
6. a kind of panoramic parking image distortion correction device, it is characterised in that including:
Model building module, under physical coordinates system, being set up centered on the image collecting device located at the wide-angle of vehicle body
One virtual cylinder, wherein, the central axis direction of the virtual cylinder is variable;
Projection module, for utilizing nominal data, picture back projection is gathered to the virtual cylinder by image collecting device
To form re-projection image;
Image output module, for the re-projection image on the virtual cylinder to be cut into output.
7. panoramic parking image distortion correction device according to claim 6, it is characterised in that the virtual cylinder is vertical
Set, to make the re-projection image as horizontal direction.
8. panoramic parking image distortion correction device according to claim 6, it is characterised in that described image harvester
For fish-eye camera.
9. panoramic parking image distortion correction device according to claim 6, it is characterised in that described image harvester
There are four, be respectively arranged on forward and backward, the left and right position of vehicle body.
10. panoramic parking image distortion correction device according to claim 6, it is characterised in that also include:Panoramic picture
Generation module, the panorama of vehicle is generated for the re-projection image obtained using each image collecting device for being correspondingly arranged at vehicle body
Image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710213788.8A CN107133912A (en) | 2017-04-01 | 2017-04-01 | Panoramic parking image distortion correction method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710213788.8A CN107133912A (en) | 2017-04-01 | 2017-04-01 | Panoramic parking image distortion correction method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107133912A true CN107133912A (en) | 2017-09-05 |
Family
ID=59715914
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710213788.8A Pending CN107133912A (en) | 2017-04-01 | 2017-04-01 | Panoramic parking image distortion correction method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107133912A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109816587A (en) * | 2017-11-20 | 2019-05-28 | 杭州海康威视数字技术股份有限公司 | A kind of fish eye images processing method, device and electronic equipment |
CN111095921A (en) * | 2017-09-20 | 2020-05-01 | 爱信精机株式会社 | Display control device |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102629372A (en) * | 2012-02-22 | 2012-08-08 | 北京工业大学 | 360 degree panoramic aerial view generation method used for assisting vehicle driving |
CN102663734A (en) * | 2012-03-15 | 2012-09-12 | 天津理工大学 | Fish eye lens calibration and fish eye image distortion correction method |
CN102729902A (en) * | 2012-07-19 | 2012-10-17 | 西北工业大学 | Embedded panoramic display device and method served for automobile safe driving |
EP2578464A1 (en) * | 2011-10-06 | 2013-04-10 | Honda Research Institute Europe GmbH | Video-based warning system for a vehicle |
CN103192766A (en) * | 2013-03-28 | 2013-07-10 | 北京工业大学 | Panorama parking assist system and application method thereof |
CN103253194A (en) * | 2013-05-17 | 2013-08-21 | 黄梅县云泰时代光学仪器有限公司 | Traveling vehicle auxiliary system |
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 |
CN103810686A (en) * | 2014-02-27 | 2014-05-21 | 苏州大学 | Seamless splicing panorama assisting driving system and method |
-
2017
- 2017-04-01 CN CN201710213788.8A patent/CN107133912A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2578464A1 (en) * | 2011-10-06 | 2013-04-10 | Honda Research Institute Europe GmbH | Video-based warning system for a vehicle |
CN102629372A (en) * | 2012-02-22 | 2012-08-08 | 北京工业大学 | 360 degree panoramic aerial view generation method used for assisting vehicle driving |
CN102663734A (en) * | 2012-03-15 | 2012-09-12 | 天津理工大学 | Fish eye lens calibration and fish eye image distortion correction method |
CN102729902A (en) * | 2012-07-19 | 2012-10-17 | 西北工业大学 | Embedded panoramic display device and method served for automobile safe driving |
CN103192766A (en) * | 2013-03-28 | 2013-07-10 | 北京工业大学 | Panorama parking assist system and application method thereof |
CN103253194A (en) * | 2013-05-17 | 2013-08-21 | 黄梅县云泰时代光学仪器有限公司 | Traveling vehicle auxiliary system |
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 |
CN103810686A (en) * | 2014-02-27 | 2014-05-21 | 苏州大学 | Seamless splicing panorama assisting driving system and method |
Non-Patent Citations (4)
Title |
---|
BAOFENG ZHANG 等: "Omnidirection Image Restoration Based On Spherical", 《APCCAS 2008 - 2008 IEEE ASIA PACIFIC CONFERENCE ON CIRCUITS AND SYSTEMS》 * |
丁刚毅 著: "《数字媒体技术》", 31 August 2015 * |
杨展览 等编: "《360°全景摄影》", 31 January 2013 * |
肖潇 等: "柱面透视投影模型下的全景环形透镜畸变校正", 《西安电子科技大学学报(自然科学版)》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111095921A (en) * | 2017-09-20 | 2020-05-01 | 爱信精机株式会社 | Display control device |
CN111095921B (en) * | 2017-09-20 | 2021-06-08 | 爱信精机株式会社 | Display control device |
CN109816587A (en) * | 2017-11-20 | 2019-05-28 | 杭州海康威视数字技术股份有限公司 | A kind of fish eye images processing method, device and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11350073B2 (en) | Disparity image stitching and visualization method based on multiple pairs of binocular cameras | |
CN111223038B (en) | Automatic splicing method of vehicle-mounted looking-around images and display device | |
CN103177439B (en) | A kind of automatic calibration method based on black and white lattice corners Matching | |
US9858639B2 (en) | Imaging surface modeling for camera modeling and virtual view synthesis | |
CN103366339B (en) | Vehicle-mounted more wide-angle camera image synthesis processing units and method | |
CN101931772B (en) | Panoramic video fusion method, system and video processing device | |
US20200366838A1 (en) | Panoramic image generation method and device | |
CN108263283A (en) | More marshalling varied angle vehicle panoramic viewing system calibration and joining method | |
CN104512328A (en) | Automobile all-round looking image generation method and automobile all-round looking system | |
CN109089074A (en) | For looking around the camera angle estimation method of monitoring system | |
JP2017220923A (en) | Image generating apparatus, image generating method, and program | |
US11050932B2 (en) | Using real time ray tracing for lens remapping | |
CN104966318A (en) | A reality augmenting method having image superposition and image special effect functions | |
CN101487895B (en) | Reverse radar system capable of displaying aerial vehicle image | |
CN106855999A (en) | The generation method and device of automobile panoramic view picture | |
EP3255604B1 (en) | Image generation device, coordinate conversion table creation device and creation method | |
CN104809719A (en) | Virtual view synthesis method based on homographic matrix partition | |
CN113870161A (en) | Vehicle-mounted 3D (three-dimensional) panoramic stitching method and device based on artificial intelligence | |
CN107798702A (en) | A kind of realtime graphic stacking method and device for augmented reality | |
CN106168988A (en) | Rule is sheltered and for the method and apparatus sheltering the image information of video camera for producing | |
CN111559314A (en) | Depth and image information fused 3D enhanced panoramic looking-around system and implementation method | |
CN107972585A (en) | Scene rebuilding System and method for is looked around with reference to the adaptive 3 D of radar information | |
CN105321160A (en) | Multi-camera calibration method for 3D panoramic parking | |
WO2016129612A1 (en) | Method for reconstructing a three-dimensional (3d) scene | |
CN107133912A (en) | Panoramic parking image distortion correction 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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170905 |
|
RJ01 | Rejection of invention patent application after publication |