CN110209997A - Depth camera automatic Calibration algorithm based on three-dimensional feature point - Google Patents
Depth camera automatic Calibration algorithm based on three-dimensional feature point Download PDFInfo
- Publication number
- CN110209997A CN110209997A CN201910495112.1A CN201910495112A CN110209997A CN 110209997 A CN110209997 A CN 110209997A CN 201910495112 A CN201910495112 A CN 201910495112A CN 110209997 A CN110209997 A CN 110209997A
- Authority
- CN
- China
- Prior art keywords
- depth camera
- camera
- depth
- coordinate
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
- G06T7/55—Depth or shape recovery from multiple images
- G06T7/593—Depth or shape recovery from multiple images from stereo images
-
- 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
- G06T7/85—Stereo camera calibration
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Pure & Applied Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention proposes a kind of depth camera automatic Calibration algorithms based on three-dimensional feature point, which, which uses two amplitude deepness images and corresponding three-dimensional feature pixel, can disposably complete the staking-out work of depth camera.Firstly, depth camera measurement model is combined to obtain the elementary proving model of depth camera with classical camera calibration model according to the coordinate and initial error offset of corresponding points in the feature pixel coordinate and depth image in known three-dimensional space；Then, camera intrinsic parameter initial value is found out by the internal reference constraint condition of depth camera, and outer parameter is found out according to internal reference initial value；Finally, optimizing established depth image control errors function to obtain the optimized parameter of depth camera.Calibration algorithm of the invention, simplify depth camera tradition peg model, it overcomes classical calibration and is illuminated by the light the shortcomings that condition and scene uncertainty etc. influence, accurately obtain camera inside and outside parameter, and have preferable repairing effect to depth image marginal distortion, have many advantages, such as that easy to operate, stated accuracy is high, practicability and robustness are good.
Description
Technical field
The invention belongs to machine vision calibration technique fields, are related to a kind of depth camera calibration algorithm, more particularly, to one
Depth camera automatic Calibration algorithm of the kind based on three-dimensional feature point
Background technique
With the development of science and technology with progress, today of various fields is spread in artificial intelligence technology, machine vision is
It is no longer a strange noun.Since NI Vision Builder for Automated Inspection has, precision is high, high-efficient, practicability is good, safe and reliable, cost
Low plurality of advantages, demand of many industries to deep vision is more and more prominent, either still raw in enterprise in scientific research institution
It is all in occupation of very important status in production.Such as in field of industrial manufacturing, vision-based detection, planning path, tracking and positioning
Deng；In life, face recognition technology, AR technology, line holographic projections technology etc., people will increasingly be unable to do without deep vision, and
Everything premise realized is to have carried out Accurate Calibration to 3D depth camera.
Although many 3D depth cameras be calibrated when leaving the factory, the parameter of calibration is simultaneously inaccurate, and camera mark
Fixed quality directly affects the superiority and inferiority of entire overall performance during manufacturing.In the prior art, there is more mature camera
Calibration algorithm, such as Zhang Zhengyou classics standardization, Tasi two-step method (documents: [1] Zhang Z.A flexible new
technique for camera calibration[C].Pattern Analysis and Machine
Intelligence.IEEE Transactions on 2000,22(11):1330-1334；[2]Tsai R.A versatile
camera calibration technique for high-accuracy 3D machine vision metrology
using off-the-shelf TV cameras and lenses[C]Robotics and Automation.IEEE,
Journal of 31987,(4):323-344.).But these methods may be only available for common optical camera, and have vulnerable to ring
The disadvantages of border influences, and demarcating steps are many and diverse, time-consuming and laborious, and calibration cost is high, and solution procedure is complicated.Depth camera imaging mode is multiple
Miscellaneous multiplicity, so that domestic and foreign scholars do not go deep into the research of depth camera calibration algorithm, their algorithm mostly structure
Complexity, stated accuracy is low, time-consuming and effort.
Nowadays, artificial intelligence is deep into all trades and professions, and 3D depth camera also progresses into people's lives, realizes depth
The simplicity of camera calibration, rapid, precision, generalization become urgent problem to be solved.It is therefore proposed that a kind of new has
It is easy to operate, at low cost, robustness is good, fast response time depth camera automatic Calibration algorithm be it is very necessary, to machine
The development of visual field and the research of the relevant technologies all have a very important significance.
Summary of the invention
In order to solve the problems, such as background technique, the purpose of the present invention is to provide a kind of based on three-dimensional feature point
Depth camera automatic Calibration algorithm proposes the concise model of depth camera calibration, introduces depth camera internal reference geometrical constraint
Condition, establish depth camera projection distortion control function, and nonlinear optimization depth camera parameter finally obtains reliable results.
The algorithm only needs two amplitude deepness images and known three-dimensional feature pixel coordinate that depth camera staking-out work can be completed, can
Suitable for becoming the special occasions such as lighting condition.
The technical solution adopted in the present invention the following steps are included:
(1) depth camera is used, accurate cube calibrating block is repeatedly shot with different postures in different location,
Obtain two accurate depth images.
Only need to obtain two width depth maps in the step (1), two amplitude deepness images of acquisition should ensure that feature is obvious
Three-dimensional feature pixel, and feature pixel should have corresponding initial error offset.
(2) three-dimensional feature in depth image is extracted using ORB (Oriented FAST and Rotated BRIEF) algorithm
Pixel information,
Then one width figure is surveyed the depth of feature pixel to the coordinate of 4 groups of feature pixel coordinates and three-dimensional space point
Amount model combines the elementary proving model to form depth camera with classical camera calibration model；The step (2) specifically includes:
Firstly, extracting two amplitude deepness images respectively using ORB (Oriented FAST and Rotated BRIEF) algorithm
4 three-dimensional feature pixels, this 4 feature pixels are generally set to the angle point of cube calibrating block, and feature pixel
There should be apparent initial error offset；Then this 4 feature pixels are matched with corresponding three-dimensional space point respectively
Obtain the coordinate of feature pixel coordinate and three-dimensional space point；And according to classical camera calibration model, such as following formula:
An original depth offset d is introduced on classical camera calibration model basisk, such as following formula:
Then, with [u v dk 1]TConstitute a projective space coordinate.With the projective space coordinate and sky of disparity map building
Between put coordinate [Xw Yw Zw 1]TRelationship meet the list between image and should be related to, thus obtain depth camera coordinate system to pixel
The matrixing of coordinate system:
Wherein, λ=Zd, ZdIndicate the coordinate components of Z-direction in depth camera coordinate system, internal reference A ':
Finally, the transition matrix of joint world coordinate system to depth camera coordinate system can show that world coordinate system is sat to pixel
Mark the transformation model of system such as:
Homography matrix is expressed as H:
(3) it is substituted into using the characteristic point pixel coordinate obtained in step 2 and known three-dimensional feature point coordinate as known quantity
In the depth camera peg model established, intrinsic parameter and outer parameter are solved according to the internal reference constraint condition of foundation；The step
Suddenly (3) specifically include:
Firstly, according to spin matrix r1,r2,r3Property establish to obtain depth camera internal reference constraint condition:
Solve A '-TA′-1:
Define one 4 dimension matrix B:
Wherein, B12=B21=B13=B31=B23=B32=0
Then, homography matrix H is write to the form of column vector as, then its i-th column vector is represented by hi=[h1i h2i
h3i h4i]T, it is obtained by the basic constraint condition of internal reference:
After abbreviation above formula:
Equation group is solved using the method that SVD is decomposed and obtains matrix B.
Secondly, carrying out the inverse decomposition of Cholesky to B:
Upper triangular matrix is converted by A ':
According to B=A '-TA′-1=(A ' A 'T)-1, obtain B-1=A ' A 'T, and:
According to B-1=A ' EA′T=A ' CCTA′T, then B-1=IIT, it obtains:
It can obtain last column element of matrix I:
Similarly:
Obtain matrix I third column, secondary series, the first column element:
I is solved out, due to A '=IC-1, thus depth camera internal reference matrix A ' initial value just be solved out.
Finally, solving outer ginseng.It is available according to internal reference constraint condition after homography matrix H and internal reference A ' is found out:
As available from the above equation:
(4) the aberration control function of Levenberg-Marquardt algorithm nonlinear optimization depth image is established and utilizes,
Optimal depth camera parameter is obtained by minimizing projection error function.The step (4) specifically includes: on n width figure
There is m point, utilize Levenberg-Marquardt algorithm nonlinear optimization re-projection error cost function:
Wherein,It is practical projection coordinate of the three-dimensional space point in depth image,
It is projection of the three-dimensional space o'clock in the i-th width figure, A ' is internal reference matrix, k1, k2, p1, p2It is distortion factor.
The utility model has the advantages that the depth camera automatic Calibration algorithm based on three-dimensional feature point that the present invention designs, it is only necessary to use
Two amplitude deepness images and known three-dimensional feature pixel avoid the influence of illumination condition bring, reduce calibration cost.This
Invent mentioned algorithm be it is fused obtain, simplify calibration process, improve stated accuracy.Compared with traditional calibration algorithm, this
Algorithm has many advantages, such as that easy to operate, adaptable, at low cost, fast response time, robustness are good.
Detailed description of the invention
Fig. 1: depth camera and three-dimensional scaling block schematic diagram；
Fig. 2: algorithm general steps flow chart；
Fig. 3: depth camera peg model derivation process figure；
Fig. 4: depth camera inside and outside parameter solution procedure figure.
Specific embodiment
1 to attached drawing 4 with reference to the accompanying drawing, and the invention will be further described.
With reference to attached drawing 3, mentioned depth camera peg model of the invention, first according to classical camera calibration model,
Such as following formula:
Then an original depth offset d is introduced on classical camera calibration model basisk, such as following formula:
Also, with [u v dk 1]TConstitute a projective space coordinate.With the projective space coordinate and sky of disparity map building
Between put coordinate [Xw Yw Zw 1]TRelationship meet the list between image and should be related to, thus obtain depth camera coordinate system to pixel
The matrixing of coordinate system:
Wherein, λ=Zd, ZdIndicate the coordinate components of Z-direction in depth camera coordinate system, internal reference A ':
The transition matrix for finally combining world coordinate system to depth camera coordinate system can show that world coordinate system is sat to pixel
Mark the transformation model of system such as:
With reference to attached drawing 1, attached drawing 3 and attached drawing 4, depth camera inside and outside parameter solving optimization process includes:
(1) according to spin matrix r1,r2,r3Property establish to obtain depth camera internal reference constraint condition:
(2) A ' is solved-TA′-1:
Define one 4 dimension matrix B:
Homography matrix H is write to the form of column vector as, then its i-th column vector is represented by as hi=[h1i h2i h3i
h4i]T, it is obtained by the basic constraint condition of internal reference:
After abbreviation above formula:
Equation group is solved using the method that SVD is decomposed and obtains matrix B.
(3) inverse decompose of Cholesky is carried out to B and obtains internal reference matrix A ':
Upper triangular matrix is converted by A ':
According to B=A '-TA′-1=(A ' A 'T)-1, obtain B-1=A ' A 'T, and:
According to B-1=A ' EA 'T=A ' CCTA′T, then B-1=IIT, it makes discovery from observation:
It can obtain last column element of matrix I:
Similarly:
Obtain matrix I third column, secondary series, the first column element:
I just is solved out, due to A '=IC-1, thus depth camera internal reference matrix A ' initial value just be solved out.
(4) outer ginseng is solved.It is available according to internal reference constraint condition after homography matrix H and internal reference A ' is found out:
As available from the above equation:
(5) the aberration control function of Levenberg-Marquardt algorithm nonlinear optimization depth image is established and utilizes,
Optimal depth camera parameter is obtained by minimizing projection error function.For having m point on n width figure, Levenberg- is utilized
Marquardt algorithm nonlinear optimization re-projection error cost function:
Wherein,It is practical projection coordinate of the three-dimensional space point in depth image,
It is projection of the three-dimensional space o'clock in the i-th width figure, A ' is internal reference matrix, k1, k2, p1, p2It is distortion factor.
By comparative test show calibration algorithm proposed in this paper compared with Zhang Shi classics calibration algorithm, calculated coke
Away from relative error less than 0.005, principal point coordinate relative error has the distortion of depth image marginal portion and preferably repairs less than 0.03
Multiple effect.With preferable practicability and robustness, achieve the purpose that depth camera is automatic, Fast Calibration.
The above content is a further detailed description of the present invention in conjunction with specific preferred embodiments, and it cannot be said that
Specific implementation of the invention is only limited to these instructions.For those of ordinary skill in the art to which the present invention belongs, exist
Under the premise of not departing from present inventive concept, several simple deduction or replace can also be made, all shall be regarded as belonging to of the invention
Protection scope.
Claims (3)
1. a kind of depth camera automatic Calibration algorithm based on three-dimensional feature point, which comprises the following steps:
Step 1: repeatedly shooting cube calibrating block with different postures in different location with depth camera, obtains two width
Depth image, two amplitude deepness images should ensure that the apparent three-dimensional feature pixel of feature, and feature pixel should have correspondence
Initial error offset；
Step 2: two width depth maps are extracted respectively first with ORB (Oriented FAST and Rotated BRIEF) algorithm
4 three-dimensional feature pixels of picture, this 4 feature pixels are generally set to the angle point of cube calibrating block, and character pixel
Point should have apparent initial error offset；Then by this 4 feature pixels respectively with corresponding three-dimensional space point carry out
With obtaining the coordinate of feature pixel coordinate and three-dimensional space point；
Step 3: depth camera measurement model is combined to the peg model to form depth camera with classical camera calibration model；
Step 4: it is substituted into using the feature pixel coordinate obtained in step 2 and known three-dimensional space point coordinate as known quantity
In the depth camera peg model that step 3 is established, depth camera is solved according to the depth camera internal reference constraint condition of foundation
Intrinsic parameter and outer parameter；
Step 5: establishing the aberration control function of depth image, and is carried out to it using Levenberg-Marquardt algorithm non-
Linear optimization, by minimize projection error function obtain optimal depth camera intrinsic parameter and outer parameter.
2. a kind of depth camera automatic Calibration algorithm based on three-dimensional feature point according to claim 1, it is characterised in that:
The step 3 specifically includes:
(1) classical camera calibration model is introduced, such as following formula:
Wherein fu=f/dx, fv=f/dy, fu, fvThe scale factor on image u axis and v axis is respectively indicated, f is camera focus, dx、
dyIt is physical size of the pixel on x, y-axis direction, (u respectively0,v0) it is principal point coordinate, R and t are the external parameters of camera.
(2) one is introduced on classical camera calibration model basis have original depth offset dkDepth camera measure mould
Type is as follows:
Wherein, C1=1/bf, C0=1/Z0, ZdIt is distance of the depth camera to object plane, Z0It is distance of the camera to reference planes,
B is the parallax range of depth camera.
(3) with [u v dk 1]TConstitute a projective space coordinate.It is sat with the projective space coordinate and spatial point of disparity map building
Mark [Xw Yw Zw 1]TRelationship meet the list between image and should be related to, thus obtain depth camera coordinate system to pixel coordinate system
Matrixing:
Wherein, λ=Zd, ZdIndicate the coordinate components of Z-direction in depth camera coordinate system, internal reference A ':
(4) transition matrix for combining world coordinate system to depth camera coordinate system can obtain world coordinate system to pixel coordinate system
Transformation model is such as:
Homography matrix is expressed as H:
There are 16 unknown parameters (4 unknown inner parameters and 12 unknown external parameters) in matrix H.For solution matrix, need
Want 4 world coordinate systems to the transformation equation of pixel coordinate system, i.e., the coordinate of 4 uncorrelated points.
3. a kind of depth camera automatic Calibration algorithm based on three-dimensional feature point according to claim 1, it is characterised in that:
The step 4 specifically includes:
(1) according to the property of spin matrix R, its column vector r can be passed through1,r2,r3Foundation obtains depth camera internal reference constraint item
Part:
(2) above-mentioned equation group is solved using the method that SVD is decomposed and obtains A '-TA′-1:
VijIt is 4 × 7 matrixes about H, and is a given value.Meanwhile having 7 unknown parameters in vector b, in order to ask
B is solved, 2 H-matrixes, i.e. 2 amplitude deepness images are needed.
(3) internal reference matrix A is solved '.
Firstly, by A ' right side multiplies an elementary matrix C and is converted into upper triangular matrix:
The inverse decomposition of Cholesky is carried out to B, obtains the 4th column, the third column, secondary series, the first column element of matrix I:
Then, I is solved out, due to A '=IC-1, thus depth camera internal reference matrix A ' initial value be solved out.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910495112.1A CN110209997A (en) | 2019-06-10 | 2019-06-10 | Depth camera automatic Calibration algorithm based on three-dimensional feature point |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910495112.1A CN110209997A (en) | 2019-06-10 | 2019-06-10 | Depth camera automatic Calibration algorithm based on three-dimensional feature point |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110209997A true CN110209997A (en) | 2019-09-06 |
Family
ID=67791635
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910495112.1A Pending CN110209997A (en) | 2019-06-10 | 2019-06-10 | Depth camera automatic Calibration algorithm based on three-dimensional feature point |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110209997A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110673122A (en) * | 2019-10-16 | 2020-01-10 | 杨清平 | Method for measuring target position data, shooting angle and camera view angle by monocular camera |
| CN111145268A (en) * | 2019-12-26 | 2020-05-12 | 四川航天神坤科技有限公司 | Video registration method and device |
| CN112270719A (en) * | 2020-12-21 | 2021-01-26 | 苏州挚途科技有限公司 | Camera calibration method, device and system |
| CN112381887A (en) * | 2020-11-17 | 2021-02-19 | 广东电科院能源技术有限责任公司 | Multi-depth camera calibration method, device, equipment and medium |
| CN112462948A (en) * | 2020-12-18 | 2021-03-09 | 哈尔滨拓博科技有限公司 | Calibration method and device based on deviation of user gesture control by depth camera |
| CN112581529A (en) * | 2020-09-22 | 2021-03-30 | 临沂大学 | Novel method for realizing rear intersection, new data processing system and storage medium |
| CN112734862A (en) * | 2021-02-10 | 2021-04-30 | 北京华捷艾米科技有限公司 | Depth image processing method and device, computer readable medium and equipment |
| CN112862895A (en) * | 2019-11-27 | 2021-05-28 | 杭州海康威视数字技术股份有限公司 | Fisheye camera calibration method, device and system |
| CN113469886A (en) * | 2021-07-23 | 2021-10-01 | 成都理工大学 | Image splicing method based on three-dimensional reconstruction |
| CN114399554A (en) * | 2021-12-08 | 2022-04-26 | 凌云光技术股份有限公司 | Calibration method and system of multi-camera system |
| CN116909208A (en) * | 2023-09-12 | 2023-10-20 | 深圳市钧诚精密制造有限公司 | Shell processing path optimization method and system based on artificial intelligence |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101630406A (en) * | 2008-07-14 | 2010-01-20 | 深圳华为通信技术有限公司 | Camera calibration method and camera calibration device |
| CN104376558A (en) * | 2014-11-13 | 2015-02-25 | 浙江大学 | Cuboid-based intrinsic parameter calibration method for Kinect depth camera |
| CN104376572A (en) * | 2014-12-02 | 2015-02-25 | 成都理工大学 | Mobile terminal camera calibrating method |
| US20170069088A1 (en) * | 2012-04-27 | 2017-03-09 | Adobe Systems Incorporated | Camera Calibration and Automatic Adjustment of Images |
| CN107507246A (en) * | 2017-08-21 | 2017-12-22 | 南京理工大学 | A kind of camera marking method based on improvement distortion model |
| CN107590832A (en) * | 2017-09-29 | 2018-01-16 | 西北工业大学 | Physical object tracking positioning method based on physical feature |
| CN108154538A (en) * | 2018-02-06 | 2018-06-12 | 华中科技大学 | A kind of twin camera module correction and scaling method and device |
| CN108510530A (en) * | 2017-02-28 | 2018-09-07 | 深圳市朗驰欣创科技股份有限公司 | A kind of three-dimensional point cloud matching process and its system |
| CN108986172A (en) * | 2018-07-25 | 2018-12-11 | 西北工业大学 | A kind of single-view linear camera scaling method towards small depth of field system |
-
2019
- 2019-06-10 CN CN201910495112.1A patent/CN110209997A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101630406A (en) * | 2008-07-14 | 2010-01-20 | 深圳华为通信技术有限公司 | Camera calibration method and camera calibration device |
| US20170069088A1 (en) * | 2012-04-27 | 2017-03-09 | Adobe Systems Incorporated | Camera Calibration and Automatic Adjustment of Images |
| CN104376558A (en) * | 2014-11-13 | 2015-02-25 | 浙江大学 | Cuboid-based intrinsic parameter calibration method for Kinect depth camera |
| CN104376572A (en) * | 2014-12-02 | 2015-02-25 | 成都理工大学 | Mobile terminal camera calibrating method |
| CN108510530A (en) * | 2017-02-28 | 2018-09-07 | 深圳市朗驰欣创科技股份有限公司 | A kind of three-dimensional point cloud matching process and its system |
| CN107507246A (en) * | 2017-08-21 | 2017-12-22 | 南京理工大学 | A kind of camera marking method based on improvement distortion model |
| CN107590832A (en) * | 2017-09-29 | 2018-01-16 | 西北工业大学 | Physical object tracking positioning method based on physical feature |
| CN108154538A (en) * | 2018-02-06 | 2018-06-12 | 华中科技大学 | A kind of twin camera module correction and scaling method and device |
| CN108986172A (en) * | 2018-07-25 | 2018-12-11 | 西北工业大学 | A kind of single-view linear camera scaling method towards small depth of field system |
Non-Patent Citations (5)
| Title |
|---|
| DONGDONG LI 等: "Depth-Camera Calibration Optimization Method Based on Homography Matrix", 《PROCEEDINGS OF THE 2019 INTERNATIONAL CONFERENCE ON ROBOTICS,INTELLIGENT CONTROL AND ARTIFICIAL INTELLIGENCE》 * |
| LIN HUANG 等: "Research on multi-camera calibration and point cloud correction method based on three-dimensional calibration object", 《OPTICS AND LASERS IN ENGINEERING》 * |
| 周杰 等: "飞行时间深度相机和彩色相机的联合标定", 《信号处理》 * |
| 李冬冬: "深度相机自动标定方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 郭连朋等: "Kinect传感器的彩色和深度相机标定", 《中国图象图形学报》 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110673122A (en) * | 2019-10-16 | 2020-01-10 | 杨清平 | Method for measuring target position data, shooting angle and camera view angle by monocular camera |
| CN112862895B (en) * | 2019-11-27 | 2023-10-10 | 杭州海康威视数字技术股份有限公司 | Fisheye camera calibration method, device and system |
| CN112862895A (en) * | 2019-11-27 | 2021-05-28 | 杭州海康威视数字技术股份有限公司 | Fisheye camera calibration method, device and system |
| CN111145268B (en) * | 2019-12-26 | 2023-10-31 | 四川航天神坤科技有限公司 | Video registration method and device |
| CN111145268A (en) * | 2019-12-26 | 2020-05-12 | 四川航天神坤科技有限公司 | Video registration method and device |
| CN112581529A (en) * | 2020-09-22 | 2021-03-30 | 临沂大学 | Novel method for realizing rear intersection, new data processing system and storage medium |
| CN112381887A (en) * | 2020-11-17 | 2021-02-19 | 广东电科院能源技术有限责任公司 | Multi-depth camera calibration method, device, equipment and medium |
| CN112462948B (en) * | 2020-12-18 | 2022-10-04 | 哈尔滨拓博科技有限公司 | Calibration method and device based on deviation of user gesture control by depth camera |
| CN112462948A (en) * | 2020-12-18 | 2021-03-09 | 哈尔滨拓博科技有限公司 | Calibration method and device based on deviation of user gesture control by depth camera |
| CN112270719B (en) * | 2020-12-21 | 2021-04-02 | 苏州挚途科技有限公司 | Camera calibration method, device and system |
| CN112270719A (en) * | 2020-12-21 | 2021-01-26 | 苏州挚途科技有限公司 | Camera calibration method, device and system |
| CN112734862A (en) * | 2021-02-10 | 2021-04-30 | 北京华捷艾米科技有限公司 | Depth image processing method and device, computer readable medium and equipment |
| CN113469886A (en) * | 2021-07-23 | 2021-10-01 | 成都理工大学 | Image splicing method based on three-dimensional reconstruction |
| CN114399554A (en) * | 2021-12-08 | 2022-04-26 | 凌云光技术股份有限公司 | Calibration method and system of multi-camera system |
| CN114399554B (en) * | 2021-12-08 | 2024-05-03 | 北京元客视界科技有限公司 | Calibration method and system of multi-camera system |
| CN116909208A (en) * | 2023-09-12 | 2023-10-20 | 深圳市钧诚精密制造有限公司 | Shell processing path optimization method and system based on artificial intelligence |
| CN116909208B (en) * | 2023-09-12 | 2023-11-24 | 深圳市钧诚精密制造有限公司 | Shell processing path optimization method and system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110209997A (en) | Depth camera automatic Calibration algorithm based on three-dimensional feature point | |
| CN105716542B (en) | A kind of three-dimensional data joining method based on flexible characteristic point | |
| CN102175261B (en) | Visual measuring system based on self-adapting targets and calibrating method thereof | |
| CN102376089B (en) | Target correction method and system | |
| CN102183214B (en) | Method for optically detecting large-aperture aspherical mirror structure | |
| CN108510551B (en) | Method and system for calibrating camera parameters under long-distance large-field-of-view condition | |
| Huang et al. | A fast and flexible projector-camera calibration system | |
| CN103048331B (en) | Printing defect detection method based on flexible template registration | |
| CN109615661A (en) | Light-field camera intrinsic parameter caliberating device and method | |
| CN105046743A (en) | Super-high-resolution three dimensional reconstruction method based on global variation technology | |
| CN111784778A (en) | Binocular camera external parameter calibration method and system based on linear solving and nonlinear optimization | |
| CN102914295A (en) | Computer vision cube calibration based three-dimensional measurement method | |
| CN104574415A (en) | Target space positioning method based on single camera | |
| CN108917633A (en) | Fuel assembly deformation detection system based on underwater binocular vision | |
| CN112161586A (en) | Line structured light vision sensor calibration method based on coding checkerboard | |
| CN112258588A (en) | Calibration method and system of binocular camera and storage medium | |
| CN102111561A (en) | Three-dimensional model projection method for simulating real scenes and device adopting same | |
| CN105989588A (en) | Irregular-shaped material cutting image correction method and system | |
| CN112815843A (en) | Online monitoring method for workpiece surface printing deviation in 3D printing process | |
| CN115861448A (en) | System calibration method and system based on angular point detection and characteristic point extraction | |
| CN104754323A (en) | Calibration method of camera optical axis detection apparatus | |
| CN103424087B (en) | A kind of large-scale steel plate three-dimensional measurement joining method | |
| CN110044266B (en) | Photogrammetry system based on speckle projection | |
| CN102111562A (en) | Projection conversion method for three-dimensional model and device adopting same | |
| CN103116888A (en) | Method for solving intrinsic parameters of cameras by plane triangles |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190906 |