CN110322485A - A kind of fast image registration method of isomery polyphaser imaging system - Google Patents
A kind of fast image registration method of isomery polyphaser imaging system Download PDFInfo
- Publication number
- CN110322485A CN110322485A CN201910553627.2A CN201910553627A CN110322485A CN 110322485 A CN110322485 A CN 110322485A CN 201910553627 A CN201910553627 A CN 201910553627A CN 110322485 A CN110322485 A CN 110322485A
- Authority
- CN
- China
- Prior art keywords
- camera
- isomery
- coordinate
- image
- matrix
- 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
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000003384 imaging method Methods 0.000 title claims abstract description 34
- 238000013507 mapping Methods 0.000 claims abstract description 16
- 230000009466 transformation Effects 0.000 claims abstract description 16
- 239000011159 matrix material Substances 0.000 claims description 22
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000013519 translation Methods 0.000 claims description 4
- 230000017105 transposition Effects 0.000 claims description 2
- 238000012545 processing Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000004927 fusion Effects 0.000 description 3
- 238000002156 mixing Methods 0.000 description 3
- 230000010287 polarization Effects 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000011045 prefiltration Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000012952 Resampling Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Studio Devices (AREA)
Abstract
The invention discloses a kind of fast image registration methods of isomery polyphaser imaging system.The step of this method includes: that the inner parameter and distortion factor of each camera are determined using Zhang Zhengyou calibration algorithm according to the scaling board image of the multiple groups different positions and pose of acquisition;Selected reference camera coordinate system, determines spatial position transformation relation of each camera relative to reference camera using stereo calibration algorithm;According to the spatial position transformation relation and target range between camera internal parameter, distortion factor, camera, coordinate mapping relations of each camera image plane relative to the reference camera plane of delineation are solved;According to coordinate mapping relationship searching table, fast image registration is realized.Method of the invention is suitable for isomery multicamera system and realizes registration in real time, is simple and efficient, practical value height.
Description
Technical field
The present invention relates to field of image processings, and more particularly, to a kind of the quick of isomery polyphaser imaging system
Method for registering images.
Background technique
Image registration techniques are the basic technologies of field of image processing, are widely used in remotely-sensed data analysis, medical image
The tasks such as analysis, computer vision.Since image sources otherness is big, general image registration techniques need to consider different answer
With the factors such as scene, different acquisition times, different acquisition visual angle, different imaging sensors, algorithm is applicable in selected.
Wherein, the method for registering images research based on feature is the most extensive, it usually needs by feature detection, feature
Match, transformation model estimation, resampling and transformation, disadvantage however is that computation complexity is high, long operational time, and is difficult to
Solve the registration problems of the biggish image pair of source differences, such as multispectral and polarization image registration.
In recent years along with the development of isomery polyphaser imaging system, such as multispectral camera system, polyphaser polarization imaging
System etc., precision and efficiency to image registration techniques propose new demand.Especially array type camera system is taken the photograph in mobile phone
As the fields such as system, automatic Pilot, panorama or three-dimensional video-frequency, monitoring security protection, light-field camera, super-resolution rebuilding are shown greatly
Application value and prospect be typically due to the difference of image intrinsic attribute, be difficult quick and precisely however in these application scenarios
Ground obtains pixel matching relationship to realize image registration, to affect the development of subsequent algorithm and application.
Summary of the invention
The purpose of the present invention is to provide a kind of fast image registration methods of isomery polyphaser imaging system, can be realized
The image of isomery polyphaser imaging system is registrated in real time.
The present invention provides a kind of fast image registration method of isomery polyphaser imaging system, comprising the following steps:
According to isomery multicamera system acquisition multiple groups different location posture clear gridiron pattern scaling board image, using
Positive friend's calibration algorithm determines the inner parameter and distortion factor of each camera;
Selected reference camera coordinate system, successively determines that each camera coordinates system is opposite using binocular vision stereo calibration algorithm
In the spatial position transformation relation of reference camera coordinate system;
According to the spatial position transformation between the camera internal parameter of isomery multicamera system, distortion factor, camera coordinates system
Relationship and the target range of setting solve Pixel-level coordinate of each camera image plane relative to the reference camera plane of delineation
Transformation relation, and construct corresponding coordinate mapping relationship searching table;
According to the coordinate mapping relationship searching table of camera each in isomery multicamera system, each camera is acquired original
Image is converted into the plane of delineation of reference camera, to realize fast image registration.
The imaging system that each camera of the isomery multicamera system is made of optics microscope group and imaging sensor.
Compared with prior art, the present invention its remarkable advantage is:
(1) a kind of fast image registration method of isomery polyphaser imaging system easy to accomplish, calculating process are proposed
Succinct and computational efficiency is high, it can be achieved that dynamic calculates in real time;
(2) fast image registration method is unrelated with image intrinsic attribute, is not influenced, is suitable for by image grayscale, feature
All kinds of isomery polyphaser imaging systems such as multispectral array camera system, polyphaser polarized systems;
(3) fast image registration method considers the distortion model of isomery multicamera system, can be completed at the same time system
Distortion correction work, to promote data precision, provide good basis for the development of subsequent algorithm and application.
Detailed description of the invention
Fig. 1 is the schematic flow chart of fast image registration method of the present invention;
Fig. 2 is the schematic flow chart of coordinates computed mapping relationship searching table in fast image registration method of the present invention;
Fig. 3 is the isomery polyphaser imaging system structural schematic diagram in the embodiment of the present invention;
Fig. 4 is the image registration schematic diagram of a scenario of the isomery multispectral camera in the embodiment of the present invention;
In figure: the preposition polarization chip arrays of 310- prefilter array, 320-, 330- image sensor array unit,
340- calculation processing unit;410,420,430,440- is original is not registrated 450nm, 550nm, 650nm, 700nm band image,
411,421,431,450nm, 550nm, 650nm, 700nm band image after 441- registration, 450,451- is original is not registrated, is registrated
Multispectral section of blending image afterwards;
Specific embodiment
The present invention is further illustrated in the following with reference to the drawings and specific embodiments.
In conjunction with Fig. 1, the present invention provides a kind of fast image registration method of isomery polyphaser imaging system, and specific steps are such as
Under:
The clear gridiron pattern scaling board figure of step 110, the multiple groups different location posture acquired according to isomery multicamera system
Picture determines the inner parameter and distortion factor of each camera using Zhang Zhengyou calibration algorithm;
It should be understood that the inner parameter Matrix C of each camera in step 110iIt can be expressed asWherein fx=
f/dxAnd fy=f/dyRepresent the focal length as unit of pixel, dxAnd dyFor the single pixel dimension of map sensor, cxAnd cyRepresent phase
Owner's point coordinate;The distortion factor matrix D of each cameraiIt can be expressed as [ki1,ki2,ki3,pi1,pi2], wherein [ki1,ki2,
ki3] coefficient of radial distortion is represented, [pi1,pi2] represent tangential distortion coefficient.
Step 120, selected reference camera coordinate system successively determine that each camera is sat using binocular vision stereo calibration algorithm
Spatial position transformation relation of the mark system relative to reference camera coordinate system;
It should be understood that spatial position transformation relation of each camera coordinates system relative to reference camera coordinate system in step 120,
Including spin matrix and R0iWith translation matrix T0i, wherein subscript " 0 " and " i " respectively represent reference camera and i-th of camera.
Step 130, according to the space between the camera internal parameter of isomery multicamera system, distortion factor, camera coordinates system
Evolution relationship and the target range of setting solve picture of each camera image plane relative to the reference camera plane of delineation
Plain grade coordinate conversion relation, and construct corresponding coordinate mapping relationship searching table;
Specifically, Fig. 2 is the schematic diagram of calculation flow of step 130 coordinate mapping relationship searching table, and implementation process is as follows:
In conjunction with Fig. 2 step 210, first by the ideal metapole p under reference camera plane of delineation coordinate system0(u, v) is thrown
Shadow is to world coordinate system the physical coordinates system of reference camera (general select) P0(X0, Y0, Z0):
Wherein, Z0Indicate the target range of setting, C0Indicate the internal reference matrix of reference camera, subscript " -1 " representing matrix
Inverse, the transposition of subscript " T " representing matrix, [u, v] value range is within the scope of image resolution ratio.
In conjunction with Fig. 2 step 220, then by the world coordinates P of target point0(X0, Y0, Z0) transform to other each cameras
Physical coordinates system obtains corresponding physical coordinates point Pi(Xi, Yi, Zi):
[Xi, Yi, Zi, 1]T=[R0i|0i][X0,Y0,Z0,1]T
Wherein, [R0i|T0i] indicate transformation matrix between reference camera coordinate system and i-th of camera coordinates system, R0iIt represents
Spin matrix, T0iRepresent translation matrix.
In conjunction with Fig. 2 step 230, then by the physical coordinates point P under each camera coordinates systemi(Xi,Yi,Zi) project to phase
The plane of delineation coordinate system for answering camera obtains Pixel-level coordinate pi(ui, vi):
[X′i,Y′i]=[Xi/Zi,Yi/Zi]
[ui,vi,1]T=Ci[X″i,Y″i,1]T
Wherein,[X′i,Y′i] it is PiNormalized coordinate, [X "i,Y″i] it is [X 'i,Y′i] distortion
Physical coordinates;[ki1,ki2,ki3,pi1,pi2] indicate i-th of camera distortion parameter, [ki1,ki2, ki3] represent radial distortion ginseng
Number, [pi1,pi2] represent tangential distortion parameter, CiIndicate the internal reference matrix of i-th of camera.
In conjunction with Fig. 2 step 240, pixel of each camera image plane relative to the reference camera plane of delineation is finally constructed
Grade coordinate conversion relation, i.e. coordinate mapping relationship searching table MAPi:
MAPi(u, v)=[ui, vi]T
Step 140, the coordinate mapping relationship searching table according to camera each in isomery multicamera system, each camera is adopted
The original image of collection is converted into the plane of delineation of reference camera, to realize fast image registration.
Specifically, realize that the method for fast image registration is directly based upon coordinate relationship look-up table in step 140:
Wherein,WithImage after respectively indicating the original image and registration of i-th of camera acquisition.
It should be noted that step 110,120 belonging to pre- calibration process, resulting camera internal parameter, distortion system are demarcated
Spatial position transformation relation between number, camera coordinates system should be used as constant and be stored.In the reality of isomery polyphaser imaging system
Step 130,140 should be successively executed in the registration task of border, i.e., first by reading the calibrating parameters stored and setting target range
To coordinates computed mapping relationship searching table (step 130), then collected original image is coordinately transformed to quickly
It is registrated to the reference camera plane of delineation (step 140).
The present invention provides a kind of fast image registration method of isomery polyphaser imaging system, this method is intrinsic with image
Attribute is unrelated, is not influenced by image grayscale, feature, and calculating is efficient, applicability is wide, may be directly applied to multispectral array camera system
All kinds of isomery polyphaser imaging systems such as system, polyphaser polarized systems, complete real-time registration task.
Embodiment
By taking the image registration task of an isomery polyphaser imaging system as an example, the present invention is described in further detail.
In conjunction with Fig. 3, the isomery polyphaser imaging system of the present embodiment includes preposition optical frames group pattern, imaging sensor battle array
Column unit 330 and calculation processing unit 340.Wherein, preposition optical frames group pattern can select filter arrays 310 or polarizing film
Array 320 respectively constitutes isomery multispectral camera system and isomery polyphaser polarized systems.
Specifically, the present embodiment carries out image registration by taking isomery multispectral camera system as an example.Wherein, isomery is multispectral
The prefilter array 310 of camera system is made of the narrow band filter slice in 6 different channels, central wavelength be respectively 450nm,
500nm, 550nm, 600nm, 650nm, 700nm, bandwidth are about 20nm, are corresponding in turn to the 0th, 1,2,3,4,5 camera;Image passes
Sensor array element 330 is made of 6 imaging sensors with model, and gray level image acquisition resolution is 1600x1300, bit wide
8bit;Calculation processing unit is embedded computer system, for executing Image Acquisition and being registrated related calculating task.
The specific implementation process of the present embodiment is as follows:
In conjunction with Fig. 1 step 110 and step 120, the pre- calibration process of isomery multispectral camera system is carried out: shooting first more
The clear gridiron pattern scaling board image of group different location posture, the inner parameter of each camera is determined using Zhang Zhengyou calibration algorithm
CiWith distortion factor Di;Then selecting No. 0 camera (corresponding 450nm wave band) is reference camera coordinate system, uses binocular vision solid
Calibration algorithm successively determines spatial position transformation relation [R of each camera coordinates system relative to No. 0 camera coordinates system0i|T0i],
Wherein i=0,1,2,3,4,5.
It should be understood that can select in isomery multispectral camera system any one camera as reference camera coordinate here
System.
Step 110 and step 120 parameters obtained, inner parameter and distortion factor, each camera including each camera are sat
Mark system is stored in calculation processing unit (340) relative to the spatial position transformation relation of No. 0 camera coordinates system.
In conjunction with Fig. 1 step 130 and Fig. 2, according to the camera internal parameter C of isomery multispectral camera systemi, distortion factor Di、
Spatial position transformation relation [R between camera coordinates system0i|T0i] and setting target range Z0, it is flat to solve each camera image
Pixel-level coordinate conversion relation of the face relative to the reference camera plane of delineation, and construct corresponding coordinate mapping relationship searching table
MAPi:
MAPi(u, v)=[ui,vi]T
Wherein i=0,1,2,3,4,5.It is the ideal coordinates point of the reference camera plane of delineation, (u in conjunction with Fig. 2, (u, v)i,vi)
For the coordinate points Jing Guo step 210,220,230 i-th obtained of camera original image plane.
In conjunction with Fig. 1 step 140, according to the coordinate mapping relationship searching table of each camera in isomery multispectral camera system
MAPi, original multispectral image that each camera is acquiredIt is converted into the plane of delineation of reference camera, to be owned
Multispectral image after registrationWherein i=0,1,2,3,4,5.
More specifically, the present embodiment isomery multispectral camera system target scene distance collected is Z in conjunction with Fig. 40=
200m, by taking wherein 4 spectral bands as an example, i.e. 450nm (correspondence image 410), 550nm (correspondence image 420), 650nm are (corresponding
Image 430), 700nm (correspondence image 440), by coordinate mapping relationship searching table MAP constructed by step 130iAct on this 4
A wave band acquired original image:
Wherein 0 < u <, 1600,0 < v < 1300.It is corresponding in turn to the original of imaging sensor acquisition
It is not registrated image 410,420,430,440,It is corresponding in turn to by isomery multiphase proposed by the present invention
Machine imaging system fast image registration method images after registration 411,421,431,441.
In conjunction with Fig. 4, multispectral section of fusion results are for more intuitively showing the Contrast on effect after not being registrated and being registrated, Central Plains
It is 550nm (correspondence image 420), 650nm (correspondence image 430) and 700nm (correspondence image that beginning and end, which are registrated blending image 450,
440) the pseudo-colours fusion results in three channels, after registration blending image 451 be 550nm (correspondence image 421), 650nm it is (corresponding
Image 431) and three channels 700nm (correspondence image 441) pseudo-colours fusion results.
Therefore, the isomery multispectral camera system of the present embodiment realizes the registration task of multispectral section of spectrum picture, after being
The development of continuous algorithm and application provides the foundation data support.The rapid registering method calculating process is succinct, computational efficiency is high, and
It is easy to expand to all kinds of isomery polyphaser imaging systems, completes real-time quick registration task.
Claims (6)
1. a kind of fast image registration method of isomery polyphaser imaging system, which comprises the steps of:
S1, according to isomery multicamera system acquisition multiple groups different location posture clear gridiron pattern scaling board image, using
Positive friend's calibration algorithm determines the inner parameter and distortion factor of each camera;
S2 selectes reference camera coordinate system, successively determines that each camera coordinates system is opposite using binocular vision stereo calibration algorithm
In the spatial position transformation relation of reference camera coordinate system;
S3 is converted according to the spatial position between the camera internal parameter of isomery multicamera system, distortion factor, camera coordinates system and is closed
The target range of system and setting, the Pixel-level coordinate for solving each camera image plane relative to the reference camera plane of delineation become
Relationship is changed, and constructs corresponding coordinate mapping relationship searching table;
S4 acquires each camera original according to the coordinate mapping relationship searching table of camera each in isomery multicamera system
Image is converted into the plane of delineation of reference camera, to realize fast image registration.
2. a kind of fast image registration method of isomery polyphaser imaging system according to claim 1, which is characterized in that
The imaging system that each camera of the isomery multicamera system is made of optics microscope group and imaging sensor.
3. a kind of fast image registration method of isomery polyphaser imaging system according to claim 1, which is characterized in that
The specific implementation process of the step S1 are as follows:
The inner parameter Matrix C of each cameraiIt can be expressed asWherein fx=f/dxAnd fy=f/dyIt represents with picture
Element is the focal length of unit, dxAnd dyFor the single pixel dimension of map sensor, cxAnd cyRepresent principal point for camera coordinate;
The distortion factor matrix D of each cameraiIt can be expressed as [kI1,ki2, ki3, pi1, pi2], wherein [ki1, ki2, ki3] represent diameter
To distortion factor, [pi1, pi2] represent tangential distortion coefficient.
4. a kind of fast image registration method of isomery polyphaser imaging system according to claim 1, which is characterized in that
The specific implementation process of the step S2 are as follows:
Select some camera of isomery multicamera system as reference camera, using its coordinate system as reference frame;
Space of each camera coordinates system relative to reference camera coordinate system is successively calculated using binocular vision stereo calibration algorithm
Evolution relationship, including spin matrix and R0iWith translation matrix T0i, wherein subscript " 0 " and " i " respectively represent reference camera and
I-th of camera.
5. a kind of fast image registration method of isomery polyphaser imaging system according to claim 1, which is characterized in that
The specific implementation process of the step S3 are as follows:
Firstly, by the ideal metapole p under reference camera plane of delineation coordinate system0(u, v) is projected to world coordinate system P0(X0,
Y0, Z0):
Wherein, Z0Indicate the target range of setting, C0Indicate reference camera internal reference matrix, subscript " -1 " representing matrix it is inverse, on
The transposition of " T " representing matrix is marked, [u, v] value range is within the scope of image resolution ratio;
Then, by the world coordinates P of target point0(X0, Y0, Z0) transform to isomery multicamera system other each cameras physics
Coordinate system obtains corresponding physical coordinates point Pi(Xi, Yi, Zi):
[Xi, Yi, Zi, 1]T=[R0i|T0i][X0, Y0, Z0, 1]T
Wherein, [R0i|T0i] indicate transformation matrix between reference camera coordinate system and i-th of camera coordinates system, R0iRepresent rotation
Matrix, T0iRepresent translation matrix;
Then, by the physical coordinates point P under each camera coordinates systemi(Xi, Yi, Zi) project to the plane of delineation coordinate of respective camera
System, obtains Pixel-level coordinate pi(ui, vi):
[X′i, Y 'i]=[Xi/Zi, Yi/Zi]
[ui, vi, 1]T=Ci[X′i, Y "i, 1]T
Wherein,[X′i, Y 'i] it is PiNormalized coordinate, [X "i, Y "i] it is [X 'i, Y 'i] distortion physics sit
Mark;[ki1, ki2, ki3, pi1, pi2] indicate i-th of camera distortion parameter, [ki1, ki2, ki3] radial distortion parameter is represented, [pi1,
pi2] represent tangential distortion parameter, CiIndicate the internal reference matrix of i-th of camera;
Finally, Pixel-level coordinate conversion relation of each camera image plane relative to the reference camera plane of delineation is constructed, that is, is sat
Mark mapping relationship searching table MAPi:
MAPi(u, v)=[ui, vi]T。
6. a kind of fast image registration method of isomery polyphaser imaging system according to claim 5, which is characterized in that
The original image that each camera acquires is converted into the plane of delineation of reference camera in the step S4:
Wherein,WithImage after respectively indicating the original image and registration of i-th of camera acquisition.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910553627.2A CN110322485B (en) | 2019-06-25 | 2019-06-25 | Rapid image registration method of heterogeneous multi-camera imaging system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910553627.2A CN110322485B (en) | 2019-06-25 | 2019-06-25 | Rapid image registration method of heterogeneous multi-camera imaging system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110322485A true CN110322485A (en) | 2019-10-11 |
CN110322485B CN110322485B (en) | 2022-08-26 |
Family
ID=68121180
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910553627.2A Active CN110322485B (en) | 2019-06-25 | 2019-06-25 | Rapid image registration method of heterogeneous multi-camera imaging system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110322485B (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110780743A (en) * | 2019-11-05 | 2020-02-11 | 聚好看科技股份有限公司 | VR (virtual reality) interaction method and VR equipment |
CN110942475A (en) * | 2019-11-13 | 2020-03-31 | 北方夜视技术股份有限公司 | Ultraviolet and visible light image fusion system and rapid image registration method |
CN112639864A (en) * | 2020-05-19 | 2021-04-09 | 华为技术有限公司 | Method and apparatus for ranging |
CN113242431A (en) * | 2021-05-13 | 2021-08-10 | 山西省交通科技研发有限公司 | Road side perception oriented labeled data preprocessing method |
CN113628283A (en) * | 2021-08-10 | 2021-11-09 | 地平线征程(杭州)人工智能科技有限公司 | Parameter calibration method and device for camera device, medium and electronic equipment |
CN113643347A (en) * | 2020-07-20 | 2021-11-12 | 黑芝麻智能科技(上海)有限公司 | Stereoscopic vision with weakly aligned heterogeneous cameras |
CN114494156A (en) * | 2022-01-03 | 2022-05-13 | 西北工业大学 | Object pose estimation and physical attribute collaborative estimation method |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160125585A1 (en) * | 2014-11-03 | 2016-05-05 | Hanwha Techwin Co., Ltd. | Camera system and image registration method thereof |
CN105758426A (en) * | 2016-02-19 | 2016-07-13 | 深圳杉川科技有限公司 | Combined calibration method for multiple sensors of mobile robot |
US20170339395A1 (en) * | 2016-05-23 | 2017-11-23 | Microsoft Technology Licensing, Llc | Imaging system comprising real-time image registration |
CN107545591A (en) * | 2016-06-29 | 2018-01-05 | 沈阳新松机器人自动化股份有限公司 | A kind of Robotic Hand-Eye Calibration method based on 6 contact methods |
CN108648240A (en) * | 2018-05-11 | 2018-10-12 | 东南大学 | Based on a non-overlapping visual field camera posture scaling method for cloud characteristics map registration |
CN109816703A (en) * | 2017-11-21 | 2019-05-28 | 西安交通大学 | A kind of point cloud registration method based on camera calibration and ICP algorithm |
-
2019
- 2019-06-25 CN CN201910553627.2A patent/CN110322485B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160125585A1 (en) * | 2014-11-03 | 2016-05-05 | Hanwha Techwin Co., Ltd. | Camera system and image registration method thereof |
CN105758426A (en) * | 2016-02-19 | 2016-07-13 | 深圳杉川科技有限公司 | Combined calibration method for multiple sensors of mobile robot |
US20170339395A1 (en) * | 2016-05-23 | 2017-11-23 | Microsoft Technology Licensing, Llc | Imaging system comprising real-time image registration |
CN107545591A (en) * | 2016-06-29 | 2018-01-05 | 沈阳新松机器人自动化股份有限公司 | A kind of Robotic Hand-Eye Calibration method based on 6 contact methods |
CN109816703A (en) * | 2017-11-21 | 2019-05-28 | 西安交通大学 | A kind of point cloud registration method based on camera calibration and ICP algorithm |
CN108648240A (en) * | 2018-05-11 | 2018-10-12 | 东南大学 | Based on a non-overlapping visual field camera posture scaling method for cloud characteristics map registration |
Non-Patent Citations (5)
Title |
---|
MYUNG-HO JU等: "Feature-Based Multi-sensor Images Alignment and Enhancement", 《2012 IEEE INTERNATIONAL SYMPOSIUM ON MULTIMEDIA》 * |
S. M. SANTHANAM等: "Lens distortion correction and geometrical alignment for Around View Monitoring system", 《THE 18TH IEEE INTERNATIONAL SYMPOSIUM ON CONSUMER ELECTRONICS (ISCE 2014)》 * |
刘永春: "光场三维成像技术研究", 《中国优秀博硕士学位论文全文数据库(博士)信息科技辑》 * |
殷惠莉等: "基于多镜头多传感器系统的图像合成", 《现代电子技术》 * |
黄楠楠等: "无人机视觉导航算法", 《红外与激光工程》 * |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110780743A (en) * | 2019-11-05 | 2020-02-11 | 聚好看科技股份有限公司 | VR (virtual reality) interaction method and VR equipment |
CN110942475A (en) * | 2019-11-13 | 2020-03-31 | 北方夜视技术股份有限公司 | Ultraviolet and visible light image fusion system and rapid image registration method |
CN110942475B (en) * | 2019-11-13 | 2023-02-17 | 北方夜视技术股份有限公司 | Ultraviolet and visible light image fusion system and rapid image registration method |
CN112639864A (en) * | 2020-05-19 | 2021-04-09 | 华为技术有限公司 | Method and apparatus for ranging |
CN113643347A (en) * | 2020-07-20 | 2021-11-12 | 黑芝麻智能科技(上海)有限公司 | Stereoscopic vision with weakly aligned heterogeneous cameras |
CN113643347B (en) * | 2020-07-20 | 2024-02-09 | 黑芝麻智能科技(上海)有限公司 | Stereoscopic vision using weakly aligned heterogeneous cameras |
CN113242431A (en) * | 2021-05-13 | 2021-08-10 | 山西省交通科技研发有限公司 | Road side perception oriented labeled data preprocessing method |
CN113628283A (en) * | 2021-08-10 | 2021-11-09 | 地平线征程(杭州)人工智能科技有限公司 | Parameter calibration method and device for camera device, medium and electronic equipment |
CN113628283B (en) * | 2021-08-10 | 2024-05-17 | 地平线征程(杭州)人工智能科技有限公司 | Parameter calibration method and device of image pickup device, medium and electronic equipment |
CN114494156A (en) * | 2022-01-03 | 2022-05-13 | 西北工业大学 | Object pose estimation and physical attribute collaborative estimation method |
CN114494156B (en) * | 2022-01-03 | 2024-03-08 | 西北工业大学 | Object pose estimation and physical attribute cooperative estimation method |
Also Published As
Publication number | Publication date |
---|---|
CN110322485B (en) | 2022-08-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110322485A (en) | A kind of fast image registration method of isomery polyphaser imaging system | |
JP6722323B2 (en) | System and method for imaging device modeling and calibration | |
CN110211043B (en) | Registration method based on grid optimization for panoramic image stitching | |
CN103198487B (en) | A kind of automatic marking method for video monitoring system | |
CN105118055B (en) | Camera position amendment scaling method and system | |
CN109919911B (en) | Mobile three-dimensional reconstruction method based on multi-view photometric stereo | |
CN107274336B (en) | A kind of Panorama Mosaic method for vehicle environment | |
CN111080724A (en) | Infrared and visible light fusion method | |
JP5739584B2 (en) | 3D image synthesizing apparatus and method for visualizing vehicle periphery | |
CN107424118A (en) | Based on the spherical panorama mosaic method for improving Lens Distortion Correction | |
CN107886547B (en) | Fisheye camera calibration method and system | |
CN101630406A (en) | Camera calibration method and camera calibration device | |
CN107154014A (en) | A kind of real-time color and depth Panorama Mosaic method | |
CN111461963B (en) | Fisheye image stitching method and device | |
CN110425983B (en) | Monocular vision three-dimensional reconstruction distance measurement method based on polarization multispectral | |
Von Gioi et al. | Towards high-precision lens distortion correction | |
CN106157246A (en) | A kind of full automatic quick cylinder panoramic image joining method | |
Lo et al. | Image stitching for dual fisheye cameras | |
CN108805921A (en) | Image-taking system and method | |
EP4242609A1 (en) | Temperature measurement method, apparatus, and system, storage medium, and program product | |
CN114529681A (en) | Hand-held double-camera building temperature field three-dimensional model construction method and system | |
CN111429356B (en) | Geometric registration and clipping method for ground hyperspectral image | |
CN109990756B (en) | Binocular ranging method and system | |
CN116012227A (en) | Image processing method, device, storage medium and processor | |
CN107147891B (en) | The adjustable three mesh depth of optical axis obtains video camera |
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 | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20210126 Address after: Room 1056, Heying building, No. 99, Tuanjie Road, Jiangbei new district, Nanjing, Jiangsu Province, 210008 Applicant after: Nanjing Zhipu Technology Co.,Ltd. Address before: 210046 Xianlin Avenue 163, Qixia District, Nanjing City, Jiangsu Province Applicant before: NANJING University |
|
TA01 | Transfer of patent application right | ||
GR01 | Patent grant | ||
GR01 | Patent grant |