CN111461963B - Fisheye image stitching method and device - Google Patents
Fisheye image stitching method and device Download PDFInfo
- Publication number
- CN111461963B CN111461963B CN202010237553.4A CN202010237553A CN111461963B CN 111461963 B CN111461963 B CN 111461963B CN 202010237553 A CN202010237553 A CN 202010237553A CN 111461963 B CN111461963 B CN 111461963B
- Authority
- CN
- China
- Prior art keywords
- fisheye
- image
- images
- coordinate system
- stitching
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000005457 optimization Methods 0.000 claims abstract description 21
- 230000000007 visual effect Effects 0.000 claims abstract description 4
- 238000006243 chemical reaction Methods 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 claims description 3
- 241000251468 Actinopterygii Species 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000003384 imaging method Methods 0.000 abstract description 6
- 238000013507 mapping Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/04—Context-preserving transformations, e.g. by using an importance map
- G06T3/047—Fisheye or wide-angle transformations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Studio Devices (AREA)
Abstract
The invention discloses a fisheye image splicing method, which comprises the following steps: s1, acquiring fish-eye images in different directions, wherein the number of the fish-eye images is more than or equal to 2, and the visual angles of the adjacent fish-eye images are overlapped; s2: extracting characteristic points in the fisheye image, and matching the characteristic points in the adjacent fisheye image to obtain characteristic point pairs; s3: establishing a joint optimization objective function of the fisheye camera projection model parameters and the image stitching registration parameters; s4: and splicing the fisheye images into panoramic images according to the optimized fisheye model parameters and the image splicing registration parameters. According to the fisheye image stitching method, the fisheye camera projection model parameters and the image stitching registration parameters are synchronously and optimally solved, the step of manually calibrating the fisheye projection model parameters is not required to be additionally added, the uncertainty and the complexity of human participation are reduced, and the projection model of the fisheye camera in actual imaging can be accurately constructed.
Description
Technical Field
The invention belongs to the technical field of image processing, and particularly relates to a splicing method of fisheye lens shooting images.
Background
And shooting a plurality of images in different directions, and splicing images overlapped between the adjacent directions to obtain a panoramic image with a larger angle of view so as to record more space information. The fisheye images can be spliced to obtain panoramic images by using fewer fisheye images due to larger field angles, so that the complexity is greatly reduced no matter the structural design of the panoramic camera, hardware deployment or later software processing, and the scheme of shooting the fisheye images by using the fisheye lens and splicing to obtain the panoramic images is widely applied.
It is known that the closer the fisheye image is to the edge of the image, the greater the distortion, so that when the fisheye projection model is constructed, the distortion parameters in the fisheye projection model are accurately calculated to be the key factors which influence the splicing effect subsequently. In the patent number CN201810654230.8, the fisheye camera is placed in a special regular hexahedron color three-dimensional calibration box to collect calibration images to calibrate imaging model parameters of the fisheye camera, no matter whether the calibration box with specific requirements is manufactured or the fisheye camera is placed in the calibration box to collect images, the operation is relatively troublesome, and the manual operation also has uncertainty; in the patent number CN201610032940.8, the inventor uses the lens mapping parameter table provided by the fisheye lens manufacturer to fit and obtain a mapping curve, the mapping curve describes the imaging relationship of the fisheye lens, and gives the corresponding relationship between the incident angle of the light and the position of the pixel point after the light is imaged on the sensor, and according to the research of the inventor, the lens mapping parameter table provided by the fisheye lens manufacturer is a theoretical value when designing the imaging relationship of the fisheye lens, and the actually produced fisheye lens has not completely satisfied the theoretical design value due to various manufacturing errors, so the problem of subsequent splicing dislocation is still caused according to the theoretical value calculation. When constructing the fish-eye projection model, since the effective area of the fish-eye image is approximately a circle, the circle center position and radius of the effective circular area of the fish-eye image need to be calculated, in the intelligent panorama generating method based on two fish-eye images, with the patent number of CN03115149.3, the boundary circle of the fish-eye image is obtained by detecting the point with intense brightness change in the fish-eye image and performing circular curve fitting, and the inventor finds that when the fish-eye lens is actually imaged, there is a transition section from the effective area to the ineffective area, the brightness change is gradual, and the fitting circle boundary cannot be determined by effectively detecting the point with intense brightness change as described in the patent number of CN03115149.3, so that errors exist in the calculated circle center and radius values, and the registration of subsequent splicing is affected.
Therefore, it is necessary to develop a method that has a high degree of automation and can solve the problem of constructing an imaging model of an actual fisheye camera and register images to be stitched with high accuracy.
Disclosure of Invention
The invention aims to: aiming at the defects of the prior art, the invention provides a fisheye image splicing method, which is used for synchronously optimizing and solving the parameters of a fisheye camera projection model and the parameters of image splicing registration, and the step of manually calibrating the parameters of the fisheye projection model is not required to be additionally added, so that the uncertainty of human participation is reduced, the automation degree of the method is high, the calculation precision is higher, and the splicing effect is better;
another object of the present invention is to provide a fisheye image stitching device using the stitching method.
The technical scheme is as follows: the invention relates to a fisheye image splicing method, which comprises the following steps:
s1, acquiring fish-eye images in different directions, wherein the number of the fish-eye images is more than or equal to 2, and the visual angles of the adjacent fish-eye images are overlapped;
s2: extracting characteristic points in the fisheye image, and matching the characteristic points in the adjacent fisheye image to obtain characteristic point pairs;
s3: establishing a joint optimization objective function of the fisheye camera projection model parameters and the image stitching registration parameters;
s4: and splicing the fisheye images into panoramic images according to the optimized fisheye model parameters and the image splicing registration parameters.
The further preferable technical scheme of the invention is that in step S2, a feature extraction algorithm, such as SIFT feature extraction algorithm, is adopted to extract feature points in the fisheye image, and the feature points in the adjacent fisheye image are matched to obtain matched feature point pairs.
Preferably, in step S3, the specific method for establishing the joint optimization objective function of the fisheye camera projection model parameter and the image stitching registration parameter is as follows:
the camera projection model refers to projecting a 3D point in a world coordinate system onto a 2D plane, and is described by equidistant projection for a fisheye camera, expressed as
r＝cθ (1)
Where c represents a scale parameter, θ represents latitude information of the incident ray, r represents a normalized radius value of the 2D point projected onto the plane from the center of the image at the 3D point, if longitude information of the incident ray is knownAnd the effective circular area radius R of the fisheye image, the coordinates (x, y) of the corresponding point on the projection back plane are expressed as
The fisheye lens radial distortion model is expressed as
r＝c 1 θ+c 2 θ 2 +c 3 θ 3 +… (3)
Wherein, c 1 ，c 2 ，c 3 .. the coefficients of the distortion polynomials, θ represents latitude information of incident light, r is a normalized projection radius, the orders of the distortion polynomials are related to fisheye cameras, and the fitting orders of different fisheye cameras are determined according to experimental effects;
let the number of fisheye images be N, and I for adjacent fisheye images i And I j The number of matching points in adjacent fish-eye images is expressed as K ij The position error of the matching feature point between the two fisheye images is
Wherein P= [ xy ]] T Representing the coordinates of the matching point pair, the transformation function f 1 (P j ) Image I j Matching feature point P in (a) j Conversion from 2D plane into 3D coordinate system
Wherein the method comprises the steps of
Wherein g represents the inverse function of equation (3), (o) x ，o y ) The center coordinates of the effective circular area of the fish eyes are represented;
conversion function f in equation (4) 2 Is to take the image I j Points in 3D coordinate systemConversion to image I i In a 3D coordinate system of (2)
[X i Y i Z i ] T ＝M[X i Y i Z i ] T (7)
Wherein M is a rotation matrix, and the conversion to the image I can be calculated by combining the formula (7) and the formula (8) i Coordinates in a 3D coordinate system of (2)
Conversion function f in equation (4) 3 In a 3D coordinate systemConversion to a 2D planar coordinate System according to equations (2) and (3)
Calculating the error of all matching pairs of image points
e＝∑e i，j (10)
The formula (10) is a joint optimization function of the projection model parameters of the fisheye camera and the image stitching registration parameters, the parameters to be solved comprise an effective circular radius, a circle center coordinate, a distortion coefficient and a rotation matrix parameter of stitching registration, and the optimization method is utilized to minimize and solve the objective function (10).
Preferably, in step S4, the specific method for stitching the fisheye image into the panoramic image according to the optimized fisheye model parameter and the image stitching registration parameter is as follows:
converting all the fisheye images from the 2D plane coordinate system to the 3D coordinate system according to the fisheye model parameters obtained by the calculation in the step S3; and then according to the rotation relation of the adjacent fisheye images under the 3D coordinate system, all the fisheye images are transformed to the same 3D coordinate system, and the overlapping parts of the images are fused under the unified coordinate system, so that the spliced panoramic image is finally obtained.
The invention relates to a fisheye image splicing device, which comprises:
the fish-eye image acquisition module is used for acquiring a plurality of fish-eye images in different shooting directions, and overlapping areas are formed between adjacent images in different directions;
the characteristic point pair selecting module is used for extracting characteristic points in the fisheye image, and matching the characteristic points in the adjacent fisheye image to obtain characteristic point pairs;
the joint optimization objective function construction module is used for establishing a joint optimization objective function of the fisheye camera projection model parameters and the image stitching registration parameters and carrying out optimization solution;
the image stitching module is used for stitching the fisheye images into panoramic images according to the optimized fisheye model parameters and the image stitching registration parameters;
each module is respectively connected with the power supply module, and is powered by the power supply module, and each module is communicated with each other through a data channel to exchange data.
The beneficial effects are that: according to the fisheye image stitching method, the fisheye camera projection model parameters and the image stitching registration parameters are synchronously and optimally solved, the step of manually calibrating the fisheye projection model parameters is not required to be additionally added, the uncertainty and the complexity of human participation are reduced, the projection model in the actual imaging of the fisheye camera can be accurately constructed, the automation degree is high, the calculation accuracy is higher, and the stitching effect is better.
Drawings
Fig. 1 is a flowchart of a fisheye image stitching method of the present invention.
Detailed Description
The technical scheme of the invention is described in detail below through the drawings, but the protection scope of the invention is not limited to the embodiments.
Examples: a fisheye image stitching method comprises the following steps:
s1, acquiring fish-eye images in different directions, wherein the number of the fish-eye images is more than or equal to 2, and the visual angles of the adjacent fish-eye images are overlapped;
s2: extracting characteristic points in the fisheye image by adopting a characteristic extraction algorithm, such as a SIFT characteristic extraction algorithm, and matching the characteristic points in the adjacent fisheye image to obtain a matched characteristic point pair;
s3: establishing a joint optimization objective function of the fisheye camera projection model parameters and the image stitching registration parameters;
the camera projection model refers to projecting a 3D point in a world coordinate system onto a 2D plane, and is described by equidistant projection for a fisheye camera, expressed as
r＝cθ (1)
Where c represents a scale parameter, θ represents latitude information of the incident ray, r represents a normalized radius value of the 2D point projected onto the plane from the center of the image at the 3D point, if longitude information of the incident ray is knownAnd the effective circular area radius R of the fisheye image, the coordinates (x, y) of the corresponding point on the projection back plane are expressed as
The fisheye lens radial distortion model is expressed as
r＝c 1 θ+c 2 θ 2 +c 3 θ 3 +… (3)
Wherein, c 1 ，c 2 ，c 3 … is a coefficient of a distortion polynomial, θ represents latitude information of incident light, r is a normalized projection radius, the order of the distortion polynomial is related to the fisheye camera, and the fitting orders of different fisheye cameras are determined according to experimental effects;
let the number of fisheye images be N, and I for adjacent fisheye images i And I j The number of matching points in adjacent fish-eye images is expressed as K ij The position error of the matching feature point between the two fisheye images is
Wherein P= [ xy ]] T Representing the coordinates of the matching point pair, the transformation function f 1 (P j ) Image I j Matching feature point P in (a) j Conversion from 2D plane into 3D coordinate system
Wherein the method comprises the steps of
Wherein g represents the inverse function of equation (3), (o) x ，o y ) The center coordinates of the effective circular area of the fish eyes are represented;
conversion function f in equation (4) 2 Is to take the image I j Points in 3D coordinate systemConversion to image I i In a 3D coordinate system of (2)
[X i Y i Z i ] T ＝M[X j Y j Z j ] T (7)
Wherein M is a rotation matrix, and the conversion to the image I can be calculated by combining the formula (7) and the formula (8) i Coordinates in a 3D coordinate system of (2)
Conversion function f in equation (4) 3 In a 3D coordinate systemConversion to 2D according to equations (2) and (3)Plane coordinate system
Calculating the error of all matching pairs of image points
e＝∑e i，j (10)
The formula (10) is a joint optimization function of the projection model parameters of the fisheye camera and the image stitching registration parameters, the parameters to be solved comprise an effective circular radius, a circle center coordinate, a distortion coefficient and a rotation matrix parameter of stitching registration, and the optimization method is utilized to minimize and solve the objective function (10);
s4: splicing the fisheye images into panoramic images according to the optimized fisheye model parameters and the image splicing registration parameters;
converting all the fisheye images from the 2D plane coordinate system to the 3D coordinate system according to the fisheye model parameters obtained by the calculation in the step S3; and then according to the rotation relation of the adjacent fisheye images under the 3D coordinate system, all the fisheye images are transformed to the same 3D coordinate system, and the overlapping parts of the images are fused under the unified coordinate system, so that the spliced panoramic image is finally obtained.
A fisheye image splicing device applying the splicing method comprises the following steps:
the fish-eye image acquisition module is used for acquiring a plurality of fish-eye images in different shooting directions, and overlapping areas are formed between adjacent images in different directions;
the characteristic point pair selecting module is used for extracting characteristic points in the fisheye image, and matching the characteristic points in the adjacent fisheye image to obtain characteristic point pairs;
the joint optimization objective function construction module is used for establishing a joint optimization objective function of the fisheye camera projection model parameters and the image stitching registration parameters and carrying out optimization solution;
the image stitching module is used for stitching the fisheye images into panoramic images according to the optimized fisheye model parameters and the image stitching registration parameters;
each module is respectively connected with the power supply module, and is powered by the power supply module, and each module is communicated with each other through a data channel to exchange data.
As described above, although the present invention has been shown and described with reference to certain preferred embodiments, it is not to be construed as limiting the invention itself. Various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (4)
1. The fisheye image splicing method is characterized by comprising the following steps of:
s1, acquiring fish-eye images in different directions, wherein the number of the fish-eye images is more than or equal to 2, and the visual angles of the adjacent fish-eye images are overlapped;
s2: extracting characteristic points in the fisheye image, and matching the characteristic points in the adjacent fisheye image to obtain characteristic point pairs;
s3: establishing a joint optimization objective function of the fisheye camera projection model parameters and the image stitching registration parameters; the specific method comprises the following steps:
the camera projection model refers to projecting a 3D point in a world coordinate system onto a 2D plane, and is described by equidistant projection for a fisheye camera, expressed as
r＝cθ (1)
Where c represents a scale parameter, θ represents latitude information of the incident ray, r represents a normalized radius value of the 2D point projected onto the plane from the center of the image at the 3D point, if longitude information of the incident ray is knownAnd the effective circular area radius R of the fisheye image, the coordinates (x, y) of the corresponding point on the projection back plane are expressed as
The fisheye lens radial distortion model is expressed as
r＝c 1 θ+c 2 θ 2 +c 3 θ 3 +…(3)
Wherein, c 1 ，c 2 ，c 3 … is a coefficient of a distortion polynomial, θ represents latitude information of incident light, r is a normalized projection radius, the order of the distortion polynomial is related to the fisheye camera, and the fitting orders of different fisheye cameras are determined according to experimental effects;
let the number of fisheye images be N, and I for adjacent fisheye images i And I j The number of matching points in adjacent fish-eye images is expressed as K ij The position error of the matching feature point between the two fisheye images is
Wherein P= [ x y ]] T Representing the coordinates of the matching point pair, the transformation function f 1 (P j ) Image I j Matching feature point P in (a) j Conversion from 2D plane into 3D coordinate system
Wherein the method comprises the steps of
Wherein g represents the inverse function of equation (3), (o) x ，o y ) The center coordinates of the effective circular area of the fish eyes are represented;
conversion function f in equation (4) 2 Is to take the image I j Points in 3D coordinate systemConversion to image I i In a 3D coordinate system of (2)
[X i Y i Z i ] T ＝M[X j Y j Z j ] T (7)
Wherein M is a rotation matrix, and the conversion to the image I can be calculated by combining the formula (7) and the formula (8) i Coordinates in a 3D coordinate system of (2)
Conversion function f in equation (4) 3 In a 3D coordinate systemConversion to a 2D planar coordinate System according to equations (2) and (3)
Calculating the error of all matching pairs of image points
e＝∑e i，j (10)
The formula (10) is a joint optimization function of the projection model parameters of the fisheye camera and the image stitching registration parameters, the parameters to be solved comprise an effective circular radius, a circle center coordinate, a distortion coefficient and a rotation matrix parameter of stitching registration, and the optimization method is utilized to minimize and solve the objective function (10);
s4: and splicing the fisheye images into panoramic images according to the optimized fisheye model parameters and the image splicing registration parameters.
2. The fisheye image stitching method according to claim 1, wherein in step S2, feature points in the fisheye image are extracted by using a feature extraction algorithm, and feature points in adjacent fisheye images are matched to obtain a matched feature point pair.
3. The fisheye image stitching method according to claim 1, wherein the specific method for stitching the fisheye image into the panoramic image according to the fisheye model parameter and the image stitching registration parameter obtained by optimization in step S4 is as follows:
converting all the fisheye images from the 2D plane coordinate system to the 3D coordinate system according to the fisheye model parameters obtained by the calculation in the step S3; and then according to the rotation relation of the adjacent fisheye images under the 3D coordinate system, all the fisheye images are transformed to the same 3D coordinate system, and the overlapping parts of the images are fused under the unified coordinate system, so that the spliced panoramic image is finally obtained.
4. A fisheye image stitching device employing the stitching method of claim 1, comprising:
the fish-eye image acquisition module is used for acquiring a plurality of fish-eye images in different shooting directions, and overlapping areas are formed between adjacent images in different directions;
the characteristic point pair selecting module is used for extracting characteristic points in the fisheye image, and matching the characteristic points in the adjacent fisheye image to obtain characteristic point pairs;
the joint optimization objective function construction module is used for establishing a joint optimization objective function of the fisheye camera projection model parameters and the image stitching registration parameters and carrying out optimization solution;
the image stitching module is used for stitching the fisheye images into panoramic images according to the optimized fisheye model parameters and the image stitching registration parameters;
each module is respectively connected with the power supply module, and is powered by the power supply module, and each module is communicated with each other through a data channel to exchange data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010237553.4A CN111461963B (en) | 2020-03-30 | 2020-03-30 | Fisheye image stitching method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010237553.4A CN111461963B (en) | 2020-03-30 | 2020-03-30 | Fisheye image stitching method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111461963A CN111461963A (en) | 2020-07-28 |
| CN111461963B true CN111461963B (en) | 2023-11-28 |
Family
ID=71683404
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010237553.4A Active CN111461963B (en) | 2020-03-30 | 2020-03-30 | Fisheye image stitching method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111461963B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112308986B (en) * | 2020-11-03 | 2024-04-12 | 豪威科技(武汉)有限公司 | Vehicle-mounted image stitching method, system and device |
| CN112734921B (en) * | 2021-01-11 | 2022-07-19 | 燕山大学 | Underwater three-dimensional map construction method based on sonar and visual image splicing |
| CN112365406B (en) * | 2021-01-13 | 2021-06-25 | 芯视界（北京）科技有限公司 | Image processing method, device and readable storage medium |
| CN114240759A (en) * | 2021-12-29 | 2022-03-25 | 交通运输部公路科学研究所 | Vehicle bottom imaging processing method and device |
| CN114372919B (en) * | 2022-03-22 | 2022-07-12 | 鹰驾科技（深圳）有限公司 | Method and system for splicing panoramic all-around images of double-trailer train |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106651767A (en) * | 2016-12-30 | 2017-05-10 | 北京星辰美豆文化传播有限公司 | Panoramic image obtaining method and apparatus |
| CN106875339A (en) * | 2017-02-22 | 2017-06-20 | 长沙全度影像科技有限公司 | A kind of fish eye images joining method based on strip scaling board |
| CN108171759A (en) * | 2018-01-26 | 2018-06-15 | 上海小蚁科技有限公司 | The scaling method of double fish eye lens panorama cameras and device, storage medium, terminal |
| CN108805801A (en) * | 2018-05-24 | 2018-11-13 | 北京华捷艾米科技有限公司 | A kind of panoramic picture bearing calibration and system |
| CN109087248A (en) * | 2018-08-22 | 2018-12-25 | 上海庄生晓梦信息科技有限公司 | A method of two different flake pictures of radius are subjected to panoramic mosaic |
-
2020
- 2020-03-30 CN CN202010237553.4A patent/CN111461963B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106651767A (en) * | 2016-12-30 | 2017-05-10 | 北京星辰美豆文化传播有限公司 | Panoramic image obtaining method and apparatus |
| CN106875339A (en) * | 2017-02-22 | 2017-06-20 | 长沙全度影像科技有限公司 | A kind of fish eye images joining method based on strip scaling board |
| CN108171759A (en) * | 2018-01-26 | 2018-06-15 | 上海小蚁科技有限公司 | The scaling method of double fish eye lens panorama cameras and device, storage medium, terminal |
| CN108805801A (en) * | 2018-05-24 | 2018-11-13 | 北京华捷艾米科技有限公司 | A kind of panoramic picture bearing calibration and system |
| CN109087248A (en) * | 2018-08-22 | 2018-12-25 | 上海庄生晓梦信息科技有限公司 | A method of two different flake pictures of radius are subjected to panoramic mosaic |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111461963A (en) | 2020-07-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111461963B (en) | Fisheye image stitching method and device | |
| JP6859442B2 (en) | Calibration equipment, calibration system, and calibration method | |
| CN106875339B (en) | Fisheye image splicing method based on strip-shaped calibration plate | |
| CN108257183B (en) | Camera lens optical axis calibration method and device | |
| TWI555379B (en) | An image calibrating, composing and depth rebuilding method of a panoramic fish-eye camera and a system thereof | |
| CN109003311B (en) | Calibration method of fisheye lens | |
| CN109064404A (en) | It is a kind of based on polyphaser calibration panorama mosaic method, panoramic mosaic system | |
| TWI555378B (en) | An image calibration, composing and depth rebuilding method of a panoramic fish-eye camera and a system thereof | |
| JP6764533B2 (en) | Calibration device, chart for calibration, chart pattern generator, and calibration method | |
| CN105096329B (en) | Method for accurately correcting image distortion of ultra-wide-angle camera | |
| CN111028155B (en) | Parallax image splicing method based on multiple pairs of binocular cameras | |
| CN107705252B (en) | Method and system suitable for splicing, unfolding and correcting binocular fisheye image | |
| CN107424118A (en) | Based on the spherical panorama mosaic method for improving Lens Distortion Correction | |
| CN102096923A (en) | Fisheye calibration method and device | |
| CN102368137B (en) | Embedded calibrating stereoscopic vision system | |
| CN112509125A (en) | Three-dimensional reconstruction method based on artificial markers and stereoscopic vision | |
| CN106952219B (en) | Image generation method for correcting fisheye camera based on external parameters | |
| CN106886976B (en) | Image generation method for correcting fisheye camera based on internal parameters | |
| CN110874854B (en) | Camera binocular photogrammetry method based on small baseline condition | |
| CN113362228A (en) | Method and system for splicing panoramic images based on improved distortion correction and mark splicing | |
| CN111383264B (en) | Positioning method, positioning device, terminal and computer storage medium | |
| CN110136205B (en) | Parallax calibration method, device and system of multi-view camera | |
| CN113516719B (en) | Camera calibration method, system and storage medium based on multiple homography matrixes | |
| CN114549666B (en) | AGV-based panoramic image splicing calibration method | |
| CN112470192A (en) | Dual-camera calibration method, electronic device and computer-readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |