CN109741455A - A kind of vehicle-mounted stereoscopic full views display methods, computer readable storage medium and system - Google Patents
A kind of vehicle-mounted stereoscopic full views display methods, computer readable storage medium and system Download PDFInfo
- Publication number
- CN109741455A CN109741455A CN201811504883.4A CN201811504883A CN109741455A CN 109741455 A CN109741455 A CN 109741455A CN 201811504883 A CN201811504883 A CN 201811504883A CN 109741455 A CN109741455 A CN 109741455A
- Authority
- CN
- China
- Prior art keywords
- image
- camera
- coordinate
- matrix
- grid model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Abstract
The present invention be suitable for it is vehicle-mounted look around field, provide a kind of vehicle-mounted stereoscopic full views display methods, computer readable storage medium and system.The described method includes: establishing three-dimensional grid model, and three-dimensional grid model is amplified to world coordinates;The fish eye images for obtaining the vehicle body surrounding of camera acquisition, carry out distortion correction, the coordinate of image and imaging center after being corrected;Camera internal reference matrix is calculated according to the coordinate of imaging center;Determine outer ginseng matrix of each camera under vehicle body coordinate system;Determine in three-dimensional space each point to the mapping relations of flat image pixel coordinate;The content of image after correction is rendered into three-dimensional grid model, realizes that stereoscopic full views look around view;Display stereoscopic full views look around view.Vehicle periphery steric environment can be more clearly shown in display window by the present invention, expanded the field range of vehicle-mounted stereoscopic full views display system, improved security performance.
Description
Technical field
It looks around field more particularly to a kind of vehicle-mounted stereoscopic full views display methods the invention belongs to vehicle-mounted, computer-readable deposit
Storage media and system.
Background technique
As being widely used for automobile further increases with vehicle intellectualized, there has also been higher to be shown to vehicle-mounted image
It is required that.The increase of automobile quantity, the limitation of road and parking stall increase the difficulty that driver travels and parks.Prior art pool
Che Shizhu ancillary equipment to be used includes side mirror, reversing radar, backsight fish eye lens etc., and also there are also a kind of using multiple wide
Vehicle periphery gets a bird's eye view drawing method in the case of angle camera acquisition depression angle.However, main problem existing for these methods is,
Can completely does not obtain vehicle-periphery image, and shown vehicle-surroundings range is smaller, in addition, birds-eye view only shows ground feelings
Condition preferably can not help driver to judge surrounding environment, therefore security performance is still poor.
Summary of the invention
The purpose of the present invention is to provide a kind of vehicle-mounted stereoscopic full views display methods, computer readable storage medium and it is
System, it is intended to which solving the prior art, can completely does not obtain vehicle-periphery image, and shown vehicle-surroundings range is smaller, separately
Outside, birds-eye view only shows surface state, preferably driver can not be helped to judge surrounding environment, therefore security performance is still
So poor problem.
In a first aspect, the present invention provides a kind of vehicle-mounted stereoscopic full views display methods, which comprises
Three-dimensional grid model is established by parametric equation, and three-dimensional grid model is amplified to world coordinates;
The fish eye images for obtaining the vehicle body surrounding of camera acquisition, carry out distortion correction, image after being corrected and at
The coordinate of inconocenter;For each camera, at least acquisition two is by plane reference board placing after different location and angle
Image;
Camera internal reference matrix is calculated according to the coordinate of imaging center;
Vehicle body coordinate system is established, measures the placement position for the plane reference plate that each camera takes in vehicle body coordinate system
World coordinates, each camera is determined according to the pixel coordinate of plane reference plate in correspondence image and camera internal reference matrix
Outer ginseng matrix under vehicle body coordinate system;
According to the outer ginseng of the corresponding camera internal reference matrix of image and each camera under vehicle body coordinate system after correction
Matrix determines in three-dimensional space each point to the mapping relations of flat image pixel coordinate;
According to the mapping relations of point each in three-dimensional space to flat image pixel coordinate, by the content of the image after correction
It is rendered into three-dimensional grid model, realizes that stereoscopic full views look around view;
Display stereoscopic full views look around view.
Second aspect, the present invention provides a kind of computer readable storage medium, the computer readable storage medium is deposited
Computer program is contained, is realized when the computer program is executed by processor such as above-mentioned vehicle-mounted stereoscopic full views display methods
Step.
The third aspect, the present invention provides a kind of vehicle-mounted stereoscopic full views display systems, comprising: one or more processors,
Memory, display and one or more computer programs, wherein the processor passes through bus respectively connects the storage
Device and the display, the display show that stereoscopic full views look around view, and one or more of computer programs are stored
In the memory, it and is configured to be executed by one or more of processors, the processor executes the calculating
It realizes when machine program such as the step of above-mentioned vehicle-mounted stereoscopic full views display methods.
In the present invention, due to first establishing three-dimensional grid model, and three-dimensional grid model is amplified to world coordinates, utilized
Camera acquires the fish eye images of vehicle body surrounding, and the content of the image after correction is rendered into three-dimensional grid model, realizes
And show that stereoscopic full views look around view.Therefore vehicle periphery steric environment can be more clearly shown in display window, expanded
The field range of vehicle-mounted stereoscopic full views display system, improves security performance.
Again due to the fish eye images using camera acquisition vehicle body surrounding, for each camera, at least acquiring two will
Image of the plane reference board placing after different location and angle;Camera internal reference matrix and each camera is calculated to sit in vehicle body
Outer ginseng matrix under mark system;According to after correction the corresponding camera internal reference matrix of image and each camera in vehicle body coordinate system
Under outer ginseng matrix, determine in three-dimensional space each point to the mapping relations of flat image pixel coordinate.Therefore vehicle of the invention
The stereo calibration method for carrying viewing system realizes that process is succinct, easy to operate, reduces the number of parameters in calculating process, is not necessarily to
The coordinate transform between camera is carried out, required acquisition picture number is fewer than conventional method, and still can guarantee the essence of calibration result
True property, does not need stereo calibration block, reduces costs.
Detailed description of the invention
Fig. 1 is the flow chart for the vehicle-mounted stereoscopic full views display methods that the embodiment of the present invention one provides.
Fig. 2 is the space length for needing to measure under vehicle body coordinate system and plane reference Board position schematic diagram.
Fig. 3 is that four road images are mapped to three-dimensional grid model schematic diagram in the embodiment of the present invention one.
Fig. 4 is the schematic diagram for the vehicle-mounted stereoscopic full views display system that the embodiment of the present invention three provides.
Specific embodiment
In order to which the purpose of the present invention, technical solution and beneficial effect is more clearly understood, below in conjunction with attached drawing and implementation
Example, the present invention will be described in further detail.It should be appreciated that specific embodiment described herein is only used to explain this hair
It is bright, it is not intended to limit the present invention.
In order to illustrate technical solutions according to the invention, the following is a description of specific embodiments.
Embodiment one:
Referring to Fig. 1, the vehicle-mounted stereoscopic full views display methods that the embodiment of the present invention one provides is the following steps are included: should be noted
If having substantially the same as a result, vehicle-mounted stereoscopic full views display methods of the invention is not with process sequence shown in FIG. 1
It is limited.
S101, three-dimensional grid model is established by parametric equation, and three-dimensional grid model is amplified to world coordinates.
In the embodiment of the present invention one, three-dimensional grid model includes planar section, curved surface coupling part and stereoscopic column face
Point, wherein planar section is the bottom surface of three-dimensional grid model, can choose circular flat, elliptic plane, round rectangle etc.;
Curved surface coupling part can choose spherical surface;Three-dimensional cylinder partial is the annular section of three-dimensional grid model.In three-dimensional grid model
The intersection point of latitude and longitude is the vertex of three-dimensional grid model.
It is described that three-dimensional grid model is amplified to world coordinates specifically:
The vertex of three-dimensional grid model is expanded into presupposition multiple, so that the vertex of three-dimensional grid model is amplified to world's seat
Mark.
By the way that three-dimensional grid model is amplified to world coordinates, it is ensured that the intersection point of the latitude and longitude in three-dimensional grid model
The vertex of the three-dimensional grid model of composition can represent a point in space, and three-dimensional grid model may include vehicle periphery
Steric environment.
S102, the fish eye images for obtaining the vehicle body surrounding acquired using camera carry out distortion correction, after being corrected
The coordinate of image and imaging center;For each camera, at least acquire two by plane reference board placing in different location and
Image after angle.
In the embodiment of the present invention one, the camera, which can be, is located at the four flake mirrors of vehicle body all around
Head.Certainly, the present invention is not limited to the quantity of camera, type and installation sites, collect 360 degree of vehicle periphery as long as can guarantee
All images information.Such as large-sized truck can collect 360 degree of panoramas of vehicle periphery using 6 to 8 camera guarantees.
The fish eye images for obtaining the vehicle body surrounding using camera acquisition, carry out distortion correction, after being corrected
The coordinate of image and imaging center is specifically as follows:
The fish eye images for obtaining the vehicle body surrounding using camera acquisition, according to the centre coordinate of camera, the wide height of pixel
Than and focal length using equidistant projection formula simulate the imaging characteristics of fish eye images, that is, pinhole imaging system formula is utilized, to fish-eye image
As carrying out distortion correction, the coordinate of image and imaging center after being corrected.
Three groups of centre coordinate, pixel aspect ratio and focal length parameters that camera is only related in the step, reduce traditional school
Multiple distortion factors in normal operation method.
Equidistant projection formula is specially r'=f θ;
Pinhole imaging system formula, i.e., normal undistorted camera imaging model specifically: r=ftan θ,
Wherein, r' is the image height in camera, and r is the image height in undistorted camera, and f is the coke of camera
Away from θ is incident light angle.
In the image after fish eye images and correction before correction the image height of each point be the point to imaging center away from
From.When initial, imaging center is the center of fish eye images and the center of the image after correction.
S103, camera internal reference matrix is calculated according to the coordinate of imaging center.
The S103 can specifically pass through formulaIt is calculated in conjunction with modes such as Zhang Zhengyou calibration methods
Camera internal reference matrix A, wherein α, β are image x, y-axis direction focal length respectively, and γ represents imaging plane obliquity factor, x0, y0It is
The coordinate of imaging center.
S104, vehicle body coordinate system is established, measures the pendulum for the plane reference plate that each camera takes in vehicle body coordinate system
The world coordinates for putting position determines every according to the pixel coordinate of plane reference plate in correspondence image and camera internal reference matrix A
Outer ginseng matrix of a camera under vehicle body coordinate system.
In the embodiment of the present invention one, all plane reference plates are placed on the same vehicle body coordinate system, avoid camera shooting
The conversion of positional relationship, reduces the complexity and calculation amount of calculating between head.As shown in Fig. 2, using vehicle body center as origin,
Floor is that X-O-Y plane establishes vehicle body coordinate system.Plane reference plate is placed on to the position of face camera, or is placed on
The overlapping region of two cameras or other be convenient for measuring the position of space coordinate, it is only necessary to guarantee at least may be used in each camera
To take the content of a width plane reference plate.
Outer ginseng matrix includes spin matrix R and translation matrix T.
S105, according to after correction the corresponding camera internal reference matrix of image and each camera under vehicle body coordinate system
Outer ginseng matrix determines in three-dimensional space each point to the mapping relations of flat image pixel coordinate.
In the embodiment of the present invention one, S105 is specifically as follows:
According to formulaDetermine that each point is sat to flat image pixel in three-dimensional space
Target mapping relations, P are the value after A [R T], that is, the mapping matrix of three-dimensional space, and s is proportionality coefficient, and A is after correcting
The corresponding camera internal reference matrix of image, [X, Y, Z] are that any one in space puts the three-dimensional coordinate under vehicle body coordinate system, R
Spin matrix in the outer ginseng matrix for being each camera under vehicle body coordinate system, T are each camera under vehicle body coordinate system
Outer ginseng matrix in translation matrix, (x, y) be in the perspective correction figure corresponding flat image pixel coordinates.
S106, according to the mapping relations of point each in three-dimensional space to flat image pixel coordinate, by the image after correction
Content be rendered into three-dimensional grid model, realize stereoscopic full views look around view.
In the embodiment of the present invention one, S106 is specifically as follows:
According to point each in three-dimensional space to the mapping relations of flat image pixel coordinate and the top of three-dimensional grid model
The space coordinate of point determines the corresponding relationship on each vertex and pixel in image in three-dimensional grid model under vehicle body coordinate system, will
The content of image after correction is rendered into the corresponding position in three-dimensional grid model according to flat image pixel coordinate, realizes vehicle
The three-dimensional mapping of ambient enviroment, obtains the complete three-dimensional environment image of vehicle periphery.As shown in figure 3, being four road fish-eye images
As being mapped to three-dimensional grid model schematic diagram.
S107, display stereoscopic full views look around view.
Ideally imaging center, that is, fish eye images center, but due to manufacture craft equal error, camera central point
Etc. parameters can be deviated.Therefore in the embodiment of the present invention one, after S102, the method can also include following step
It is rapid:
Camera parameter is refined, and the image after accurately being corrected according to accurate camera parameter.
It is specifically as follows: traverses the initial parameter of camera within a preset range, pass through the calibration point of plane reference plate in fish eye images
Pixel coordinate and parameter value, the calibration point pixel of plane reference plate in the pixel coordinate after being mapped, with the image after correction
Coordinate compares, and obtains accurate camera parameter, and the image after accurately being corrected according to accurate camera parameter.
Since stereoscopic full views look around the image for needing to acquire different cameras and shooting, the locality of camera and illumination are strong
Spending different equal influences leads to color of image difference.Therefore, in the embodiment of the present invention one, after S105, the method may be used also
With the following steps are included:
The color of image of image after correction is corrected, caused luminance difference after different camera shootings is eliminated.
The color of image of image after described pair of correction is corrected specifically:
By the minimum objective function of the color difference of the two images of image overlapping region, respectively to tri- channel systems of RGB
Number passes through following formula F=(fFAF-fLAL)2+(fFBF-fRBR)2+(fLCL-fTCT)2+(fRDR-fTDT)2It is set, wherein
fF,fT,fL,fRRespectively represent the luminance factor of view all around, AF,ALBefore respectively representing in front view and left view overlay region
View pixels mean value and left view pixel mean value, BF,,BRIt respectively represents front view and front view pixel in right view overlay region is equal
Value and right view pixel mean value, CL,CTRespectively represent left view pixel mean value and backsight image in left view and rearview overlay region
Plain mean value, DR,DTRight view pixel mean value and rearview pixel mean value in right view and rearview overlay region are respectively represented, it is right
Luminance factor seeks local derviation respectively, and the luminance factor F of each view is found out by singular value decomposition.
In order to avoid there are obvious splicing traces after two images splicing, in the embodiment of the present invention one,
The color of image of image after S105 or described pair of correction is corrected, and eliminates caused luminance difference after different cameras shootings
After different, the method can with the following steps are included:
The overlapping region to be formed is shot for two cameras, splicing trace is eliminated by Weighted Fusion.It is specifically as follows:
Pass through formula I (x, y)=w1I1(x,y)+w2I2(x, y) eliminates splicing trace, wherein I1(x, y) and I2(x, y) is
Pixel value of the view of overlapping region two in the position (x, y), w1And w2It is weight coefficient, seam or non-can be fixed according to distance
The distance of fixed seam determines.In the embodiment of the present invention one, each point distance in the determination basis overlapping region of weight coefficient
The Edge Distance of two width views.I.e. weighting coefficient is that each point of overlay region one side edge is decremented to 0 by 1 along horizontal direction.
In the embodiment of the present invention one, S107 is specifically as follows:
The vehicle running state obtained according to onboard sensor is (such as differences such as vehicle turning, reversing, normally travels
Situation), show that the stereoscopic full views of different angle and range look around view in three-dimensional grid model in vehicle display window.
Embodiment two:
Second embodiment of the present invention provides a kind of computer readable storage medium, the computer-readable recording medium storage
There is computer program, realizes that the vehicle-mounted solid provided such as the embodiment of the present invention one is full when the computer program is executed by processor
The step of scape display methods.
Embodiment three:
Fig. 4 shows the schematic diagram of the vehicle-mounted stereoscopic full views display system of the offer of the embodiment of the present invention three, a kind of vehicle-mounted vertical
Body panorama display system 100 includes: one or more processors 101, memory 102, display 103 and one or more meters
Calculation machine program, wherein the processor 101 connects the memory 102 and the display 103 by bus respectively, it is described aobvious
Showing that device 103 shows that stereoscopic full views look around view, one or more of computer programs are stored in the memory 102,
And it is configured to be executed by one or more of processors 101, the processor 101 executes real when the computer program
Now such as the step of the vehicle-mounted stereoscopic full views display methods of the offer of the embodiment of the present invention one.
In the present invention, due to first establishing three-dimensional grid model, and three-dimensional grid model is amplified to world coordinates, utilized
Camera acquires the fish eye images of vehicle body surrounding, and the content of the image after correction is rendered into three-dimensional grid model, realizes
And show that stereoscopic full views look around view.Therefore vehicle periphery steric environment can be more clearly shown in display window, expanded
The field range of vehicle-mounted stereoscopic full views display system, improves security performance.
Due to the fish eye images using camera acquisition vehicle body surrounding, for each camera, at least acquiring two will be put down
Face scaling board is placed in the image after different location and angle;Camera internal reference matrix and each camera are calculated in vehicle body coordinate
Outer ginseng matrix under system;According to after correction the corresponding camera internal reference matrix of image and each camera under vehicle body coordinate system
Outer ginseng matrix, determine in three-dimensional space each point to the mapping relations of flat image pixel coordinate.Therefore of the invention vehicle-mounted
The stereo calibration method of viewing system realizes that process is succinct, easy to operate, reduces the number of parameters in calculating process, without into
Coordinate transform between row camera, required acquisition picture number is fewer than conventional method, and still can guarantee the accurate of calibration result
Property, stereo calibration block is not needed, is reduced costs.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of above-described embodiment is can
It is completed with instructing relevant hardware by program, which can be stored in a computer readable storage medium, storage
Medium may include: read-only memory (ROM, Read Only Memory), random access memory (RAM, Random
Access Memory), disk or CD etc..
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Made any modifications, equivalent replacements, and improvements etc., should all be included in the protection scope of the present invention within mind and principle.
Claims (10)
1. a kind of vehicle-mounted stereoscopic full views display methods, which is characterized in that the described method includes:
Three-dimensional grid model is established by parametric equation, and three-dimensional grid model is amplified to world coordinates;
The fish eye images for obtaining the vehicle body surrounding of camera acquisition, carry out distortion correction, in the image and imaging after being corrected
The coordinate of the heart;For each camera, two images by plane reference board placing after different location and angle are at least acquired;
Camera internal reference matrix is calculated according to the coordinate of imaging center;
Vehicle body coordinate system is established, measures the generation of the placement position for the plane reference plate that each camera takes in vehicle body coordinate system
Boundary's coordinate determines each camera in vehicle according to the pixel coordinate of plane reference plate in correspondence image and camera internal reference matrix
Outer ginseng matrix under body coordinate system;
According to the outer ginseng matrix of the corresponding camera internal reference matrix of image and each camera under vehicle body coordinate system after correction,
Determine in three-dimensional space each point to the mapping relations of flat image pixel coordinate;
According to the mapping relations of point each in three-dimensional space to flat image pixel coordinate, the content of the image after correction is rendered
Into three-dimensional grid model, realize that stereoscopic full views look around view;
Display stereoscopic full views look around view.
2. the method as described in claim 1, which is characterized in that the three-dimensional grid model includes planar section, curved surface connection
Part and three-dimensional cylinder partial, wherein planar section is the bottom surface of three-dimensional grid model, and three-dimensional cylinder partial is three-dimensional grid mould
The annular section of type;The intersection point of latitude and longitude is the vertex of three-dimensional grid model in three-dimensional grid model;
It is described that three-dimensional grid model is amplified to world coordinates specifically:
The vertex of three-dimensional grid model is expanded into presupposition multiple, so that the vertex of three-dimensional grid model is amplified to world coordinates;
The fish eye images for obtaining the vehicle body surrounding using camera acquisition, carry out distortion correction, the image after being corrected
With the coordinate of imaging center specifically:
Obtain using camera acquisition vehicle body surrounding fish eye images, according to the centre coordinate of camera, pixel aspect ratio and
Focal length simulates the imaging characteristics of fish eye images using equidistant projection formula, that is, utilize pinhole imaging system formula, to fish eye images into
Line distortion correction, the coordinate of image and imaging center after being corrected;
Camera internal reference matrix is calculated in the coordinate according to imaging center specifically:
Pass through formulaCamera internal reference matrix A is calculated in conjunction with Zhang Zhengyou calibration method, wherein α, β
It is image x, y-axis direction focal length respectively, γ represents imaging plane obliquity factor, x0, y0It is the coordinate of imaging center.
3. the method as described in claim 1, which is characterized in that the outer ginseng matrix includes spin matrix and translation matrix;
The outer ginseng of the corresponding camera internal reference matrix of image and each camera under vehicle body coordinate system according to after correction
Matrix determines in three-dimensional space each point to the mapping relations of flat image pixel coordinate specifically:
According to formulaDetermine in three-dimensional space each point to flat image pixel coordinate
Mapping relations, P are the mapping matrixes of three-dimensional space, and s is proportionality coefficient, and A is the corresponding camera internal reference square of image after correction
Battle array, [X, Y, Z] are that any one in space puts the three-dimensional coordinate under vehicle body coordinate system, and R is each camera in vehicle body coordinate
The spin matrix in outer ginseng matrix under system, T are translation matrix of each camera in the outer ginseng matrix under vehicle body coordinate system,
(x, y) is the corresponding flat image pixel coordinates in the perspective correction figure.
4. the method as described in claim 1, which is characterized in that described according to point each in three-dimensional space to flat image pixel
The content of image after correction is rendered into three-dimensional grid model by the mapping relations of coordinate, realizes that stereoscopic full views look around view
Specifically:
According to point each in three-dimensional space to the mapping relations of flat image pixel coordinate and the vertex of three-dimensional grid model
Space coordinate determines the corresponding relationship on each vertex and pixel in image in three-dimensional grid model under vehicle body coordinate system, will correct
The content of image afterwards is rendered into the corresponding position in three-dimensional grid model according to flat image pixel coordinate, realizes vehicle periphery
The three-dimensional mapping of environment, obtains the complete three-dimensional environment image of vehicle periphery.
5. the method as described in claim 1, which is characterized in that in the corresponding camera internal reference of image according to after correction
The outer ginseng matrix of matrix and each camera under vehicle body coordinate system determines that each point is sat to flat image pixel in three-dimensional space
After target mapping relations, the method also includes:
The color of image of image after correction is corrected, caused luminance difference after different camera shootings is eliminated.
6. method as claimed in claim 5, which is characterized in that the color of image of the image after described pair of correction is corrected tool
Body are as follows:
It is logical to tri- channel factors of RGB respectively by the minimum objective function of the color difference of the two images of image overlapping region
Cross following formula F=(fFAF-fLAL)2+(fFBF-fRBR)2+(fLCL-fTCT)2+(fRDR-fTDT)2It is set, wherein fF, fT,
fL, fRRespectively represent the luminance factor of view all around, AF, ALRespectively represent front view in front view and left view overlay region
Pixel mean value and left view pixel mean value, BF, BRRespectively represent in front view and right view overlay region front view pixel mean value and
Right view pixel mean value, CL, CTIt respectively represents left view and left view pixel mean value in rearview overlay region and rearview pixel is equal
Value, DR, DTRight view pixel mean value and rearview pixel mean value in right view and rearview overlay region are respectively represented, to brightness
Coefficient seeks local derviation respectively, and the luminance factor F of each view is found out by singular value decomposition.
7. method as claimed in claim 5, which is characterized in that in the corresponding camera internal reference of image according to after correction
The outer ginseng matrix of matrix and each camera under vehicle body coordinate system determines that each point is sat to flat image pixel in three-dimensional space
Target mapping relations are led after eliminating different camera shootings alternatively, the color of image of the image after described pair of correction is corrected
After the luminance difference of cause, the method also includes:
The overlapping region to be formed is shot for two cameras, splicing trace is eliminated by Weighted Fusion.
8. the method for claim 7, which is characterized in that it is described that the overlapping region to be formed is shot for two cameras,
Splicing trace is eliminated by Weighted Fusion specifically:
Pass through formula I (x, y)=w1I1(x, y)+w2I2(x, y) eliminates splicing trace, wherein I1(x, y) and I2(x, y) is overlapping
Pixel value of two, the region view in the position (x, y), w1And w2It is weight coefficient.
9. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In the computer program realizes that vehicle-mounted stereoscopic full views as claimed in any one of claims 1 to 8 are shown when being executed by processor
The step of method.
10. a kind of vehicle-mounted stereoscopic full views display system, comprising: one or more processors, memory, display and one or
Multiple computer programs, wherein the processor passes through bus respectively connects the memory and the display, the display
Device shows that stereoscopic full views look around view, and one or more of computer programs are stored in the memory, and are matched
It is set to and is executed by one or more of processors, which is characterized in that the processor is realized when executing the computer program
The step of vehicle-mounted stereoscopic full views display methods as claimed in any one of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811504883.4A CN109741455B (en) | 2018-12-10 | 2018-12-10 | Vehicle-mounted stereoscopic panoramic display method, computer readable storage medium and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811504883.4A CN109741455B (en) | 2018-12-10 | 2018-12-10 | Vehicle-mounted stereoscopic panoramic display method, computer readable storage medium and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109741455A true CN109741455A (en) | 2019-05-10 |
CN109741455B CN109741455B (en) | 2022-11-29 |
Family
ID=66358756
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811504883.4A Active CN109741455B (en) | 2018-12-10 | 2018-12-10 | Vehicle-mounted stereoscopic panoramic display method, computer readable storage medium and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109741455B (en) |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111223038A (en) * | 2019-12-02 | 2020-06-02 | 上海赫千电子科技有限公司 | Automatic splicing method and display device for vehicle-mounted all-around images |
CN111783597A (en) * | 2020-06-24 | 2020-10-16 | 中国第一汽车股份有限公司 | Method and device for calibrating driving trajectory, computer equipment and storage medium |
CN111815752A (en) * | 2020-07-16 | 2020-10-23 | 展讯通信(上海)有限公司 | Image processing method and device and electronic equipment |
CN111899307A (en) * | 2020-07-30 | 2020-11-06 | 浙江大学 | Space calibration method, electronic device and storage medium |
CN112235488A (en) * | 2020-06-08 | 2021-01-15 | 威盛电子股份有限公司 | Automatic correction method for vehicle-mounted lens and vehicle-mounted lens device |
CN112241930A (en) * | 2019-07-18 | 2021-01-19 | 杭州海康威视数字技术股份有限公司 | Vehicle-mounted all-round looking method, device and system and vehicle |
CN112465920A (en) * | 2020-12-08 | 2021-03-09 | 广州小鹏自动驾驶科技有限公司 | Vision sensor calibration method and device |
CN113066158A (en) * | 2019-12-16 | 2021-07-02 | 杭州海康威视数字技术股份有限公司 | Vehicle-mounted all-round looking method and device |
CN113065999A (en) * | 2019-12-16 | 2021-07-02 | 杭州海康威视数字技术股份有限公司 | Vehicle-mounted panorama generation method and device, image processing equipment and storage medium |
CN113132708A (en) * | 2021-04-22 | 2021-07-16 | 北京房江湖科技有限公司 | Method and apparatus for acquiring three-dimensional scene image using fisheye camera, device and medium |
CN113421183A (en) * | 2021-05-31 | 2021-09-21 | 中汽数据(天津)有限公司 | Method, device and equipment for generating vehicle panoramic view and storage medium |
CN113496520A (en) * | 2020-04-02 | 2021-10-12 | 北京四维图新科技股份有限公司 | Method and device for turning top view of camera and storage medium |
CN113516717A (en) * | 2020-04-10 | 2021-10-19 | 富华科精密工业(深圳)有限公司 | Camera device external parameter calibration method, electronic equipment and storage medium |
CN114598822A (en) * | 2022-03-02 | 2022-06-07 | 上海赫千电子科技有限公司 | Vehicle-mounted Ethernet all-around system with ESD interference resistance |
CN115797467A (en) * | 2023-02-02 | 2023-03-14 | 深圳市德驰微视技术有限公司 | Method, device and equipment for detecting calibration result of vehicle camera and storage medium |
CN116740681A (en) * | 2023-08-10 | 2023-09-12 | 小米汽车科技有限公司 | Target detection method, device, vehicle and storage medium |
WO2023226570A1 (en) * | 2022-05-23 | 2023-11-30 | 中兴通讯股份有限公司 | Field-of-view enlarging method, electronic device and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140193079A1 (en) * | 2013-01-10 | 2014-07-10 | Realtek Semiconductor Corp. | Image correction method using approximately non-linear regression approach and related image correction circuit |
CN107767422A (en) * | 2017-09-18 | 2018-03-06 | 深圳开阳电子股份有限公司 | A kind of fish-eye bearing calibration, device and portable terminal |
CN107888894A (en) * | 2017-10-12 | 2018-04-06 | 浙江零跑科技有限公司 | A kind of solid is vehicle-mounted to look around method, system and vehicle-mounted control device |
CN108765496A (en) * | 2018-05-24 | 2018-11-06 | 河海大学常州校区 | A kind of multiple views automobile looks around DAS (Driver Assistant System) and method |
-
2018
- 2018-12-10 CN CN201811504883.4A patent/CN109741455B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140193079A1 (en) * | 2013-01-10 | 2014-07-10 | Realtek Semiconductor Corp. | Image correction method using approximately non-linear regression approach and related image correction circuit |
CN107767422A (en) * | 2017-09-18 | 2018-03-06 | 深圳开阳电子股份有限公司 | A kind of fish-eye bearing calibration, device and portable terminal |
CN107888894A (en) * | 2017-10-12 | 2018-04-06 | 浙江零跑科技有限公司 | A kind of solid is vehicle-mounted to look around method, system and vehicle-mounted control device |
CN108765496A (en) * | 2018-05-24 | 2018-11-06 | 河海大学常州校区 | A kind of multiple views automobile looks around DAS (Driver Assistant System) and method |
Non-Patent Citations (2)
Title |
---|
UTKARSH TIWARI: "Non-linear method used for distortion correction of fish-eye lens: Comparative analysis of different mapping functions", 《2015 INTERNATIONAL CONFERENCE ON MAN AND MACHINE INTERFACING (MAMI)》 * |
常嘉义: "全景鸟瞰拼接图像的质量评价方法", 《计算机科学》 * |
Cited By (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112241930A (en) * | 2019-07-18 | 2021-01-19 | 杭州海康威视数字技术股份有限公司 | Vehicle-mounted all-round looking method, device and system and vehicle |
CN111223038B (en) * | 2019-12-02 | 2023-06-09 | 上海赫千电子科技有限公司 | Automatic splicing method of vehicle-mounted looking-around images and display device |
CN111223038A (en) * | 2019-12-02 | 2020-06-02 | 上海赫千电子科技有限公司 | Automatic splicing method and display device for vehicle-mounted all-around images |
CN113065999A (en) * | 2019-12-16 | 2021-07-02 | 杭州海康威视数字技术股份有限公司 | Vehicle-mounted panorama generation method and device, image processing equipment and storage medium |
CN113066158B (en) * | 2019-12-16 | 2023-03-10 | 杭州海康威视数字技术股份有限公司 | Vehicle-mounted all-round looking method and device |
CN113065999B (en) * | 2019-12-16 | 2023-03-10 | 杭州海康威视数字技术股份有限公司 | Vehicle-mounted panorama generation method and device, image processing equipment and storage medium |
CN113066158A (en) * | 2019-12-16 | 2021-07-02 | 杭州海康威视数字技术股份有限公司 | Vehicle-mounted all-round looking method and device |
CN113496520A (en) * | 2020-04-02 | 2021-10-12 | 北京四维图新科技股份有限公司 | Method and device for turning top view of camera and storage medium |
CN113516717A (en) * | 2020-04-10 | 2021-10-19 | 富华科精密工业(深圳)有限公司 | Camera device external parameter calibration method, electronic equipment and storage medium |
CN112235488A (en) * | 2020-06-08 | 2021-01-15 | 威盛电子股份有限公司 | Automatic correction method for vehicle-mounted lens and vehicle-mounted lens device |
CN112235488B (en) * | 2020-06-08 | 2022-06-10 | 威盛电子股份有限公司 | Automatic correction method for vehicle-mounted lens and vehicle-mounted lens device |
CN111783597A (en) * | 2020-06-24 | 2020-10-16 | 中国第一汽车股份有限公司 | Method and device for calibrating driving trajectory, computer equipment and storage medium |
CN111815752B (en) * | 2020-07-16 | 2022-11-29 | 展讯通信(上海)有限公司 | Image processing method and device and electronic equipment |
CN111815752A (en) * | 2020-07-16 | 2020-10-23 | 展讯通信(上海)有限公司 | Image processing method and device and electronic equipment |
CN111899307B (en) * | 2020-07-30 | 2023-12-29 | 浙江大学 | Space calibration method, electronic equipment and storage medium |
CN111899307A (en) * | 2020-07-30 | 2020-11-06 | 浙江大学 | Space calibration method, electronic device and storage medium |
CN112465920A (en) * | 2020-12-08 | 2021-03-09 | 广州小鹏自动驾驶科技有限公司 | Vision sensor calibration method and device |
CN113132708B (en) * | 2021-04-22 | 2022-02-22 | 贝壳找房(北京)科技有限公司 | Method and apparatus for acquiring three-dimensional scene image using fisheye camera, device and medium |
CN113132708A (en) * | 2021-04-22 | 2021-07-16 | 北京房江湖科技有限公司 | Method and apparatus for acquiring three-dimensional scene image using fisheye camera, device and medium |
CN113421183B (en) * | 2021-05-31 | 2022-09-20 | 中汽数据(天津)有限公司 | Method, device and equipment for generating vehicle panoramic view and storage medium |
CN113421183A (en) * | 2021-05-31 | 2021-09-21 | 中汽数据(天津)有限公司 | Method, device and equipment for generating vehicle panoramic view and storage medium |
CN114598822A (en) * | 2022-03-02 | 2022-06-07 | 上海赫千电子科技有限公司 | Vehicle-mounted Ethernet all-around system with ESD interference resistance |
WO2023226570A1 (en) * | 2022-05-23 | 2023-11-30 | 中兴通讯股份有限公司 | Field-of-view enlarging method, electronic device and storage medium |
CN115797467A (en) * | 2023-02-02 | 2023-03-14 | 深圳市德驰微视技术有限公司 | Method, device and equipment for detecting calibration result of vehicle camera and storage medium |
CN116740681A (en) * | 2023-08-10 | 2023-09-12 | 小米汽车科技有限公司 | Target detection method, device, vehicle and storage medium |
CN116740681B (en) * | 2023-08-10 | 2023-11-21 | 小米汽车科技有限公司 | Target detection method, device, vehicle and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN109741455B (en) | 2022-11-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109741455A (en) | A kind of vehicle-mounted stereoscopic full views display methods, computer readable storage medium and system | |
CN109712194A (en) | Vehicle-mounted viewing system and its stereo calibration method and computer readable storage medium | |
CN111223038B (en) | Automatic splicing method of vehicle-mounted looking-around images and display device | |
KR101265667B1 (en) | Device for 3d image composition for visualizing image of vehicle around and method therefor | |
CN104851076B (en) | Panoramic looking-around parking assisting system and camera installation method for commercial car | |
US6778207B1 (en) | Fast digital pan tilt zoom video | |
CN110244282B (en) | Multi-camera system and laser radar combined system and combined calibration method thereof | |
CN110288527B (en) | Panoramic aerial view generation method of vehicle-mounted panoramic camera | |
CN112224132A (en) | Vehicle panoramic all-around obstacle early warning method | |
CN106464847A (en) | Image synthesis system, image synthesis device therefor, and image synthesis method | |
JP2011215063A (en) | Camera attitude parameter estimation device | |
CN107767422A (en) | A kind of fish-eye bearing calibration, device and portable terminal | |
CN101236654A (en) | Method and apparatus for camera calibration, and vehicle | |
CN103617606A (en) | Vehicle multi-angle panorama generating method for aided driving | |
JP2008187564A (en) | Camera calibration apparatus and method, and vehicle | |
CN105488766B (en) | Fisheye image bearing calibration and device | |
CN109948398A (en) | The image processing method and panorama parking apparatus that panorama is parked | |
CN108805910A (en) | More mesh Train-borne recorders, object detection method, intelligent driving system and automobile | |
GB2561329A (en) | Method and system for creating images | |
CN112233188B (en) | Calibration method of data fusion system of laser radar and panoramic camera | |
CN107993264A (en) | A kind of automobile looks around the scaling method of panorama | |
CN109087251A (en) | A kind of vehicle-mounted panoramic image display method and system | |
CN110264395A (en) | A kind of the camera lens scaling method and relevant apparatus of vehicle-mounted monocular panorama system | |
CN108596982A (en) | A kind of easy vehicle-mounted multi-view camera viewing system scaling method and device | |
CN111640062A (en) | Automatic splicing method for vehicle-mounted all-around images |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |