CN109522935A - The method that the calibration result of a kind of pair of two CCD camera measure system is evaluated - Google Patents
The method that the calibration result of a kind of pair of two CCD camera measure system is evaluated Download PDFInfo
- Publication number
- CN109522935A CN109522935A CN201811232049.4A CN201811232049A CN109522935A CN 109522935 A CN109522935 A CN 109522935A CN 201811232049 A CN201811232049 A CN 201811232049A CN 109522935 A CN109522935 A CN 109522935A
- Authority
- CN
- China
- Prior art keywords
- calibration result
- coordinate
- camera
- image
- scaling board
- 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 30
- 239000011159 matrix material Substances 0.000 claims abstract description 42
- 238000013519 translation Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 abstract description 13
- 238000001514 detection method Methods 0.000 abstract description 4
- 241000208340 Araliaceae Species 0.000 abstract description 2
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 abstract description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 abstract description 2
- 235000008434 ginseng Nutrition 0.000 abstract description 2
- 238000005259 measurement Methods 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
-
- 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
Abstract
The invention discloses the methods that the calibration result of a kind of pair of two CCD camera measure system is evaluated, picpointed coordinate of the mark point in left images in the inside and outside ginseng and scaling board obtained using calibration, calculate three-dimensional coordinate of the calibration point under camera coordinates system, this three-dimensional coordinate is transformed into world coordinate system again and obtains the space coordinate measured value of mark point, calculate the Euclidean distance between the space coordinate measured value and the actual coordinate value of mark point, multiple mark points in scaling board under the different calibration poses obtained to shooting, seek the mean value of Euclidean distance, and judge whether calibration result is correct；This method carries out calibration result precision evaluation to two CCD camera measure system, and evaluation method is more reasonable；The method of the present invention also evaluates basis matrix, provides safeguard for the matching process of subsequent biocular systems, and it is accurate that the present invention evaluates the stated accuracy of binocular vision detection system, has wide applicability.
Description
Technical field
The present invention relates to Machine Vision Detection fields, and in particular to the calibration result of a kind of pair of two CCD camera measure system
The method evaluated.
Background technique
Two CCD camera measure system is to take pictures to carry out image and adopt to target object from different perspectives using two video cameras
Collection, and the three-dimensional information for reconstructing target in three dimensions has to realize the detection of object appearance in vision measurement field
It is widely applied, and the calibration process of two CCD camera measure system is indispensable link in measurement, such as Zhang Shi standardization,
It is demarcated using plane reference plate, the precision of calibration result has been largely fixed the precision of subsequent measurement, therefore,
It after the completion of two CCD camera measure system calibration, needs to verify, whether the precision of evaluation calibration result meets measurement request.
Current existing evaluation method is back projection error analysis method, and this method is three-dimensional by the mark point on scaling board
Coordinate is converted to the two-dimensional coordinate on the plane of delineation by the transition matrix that calibration obtains, and then calculates measurement point and ideal point
The distance between, such evaluation method calculates on 2d, mainly to the evaluation of inside and outside parameter.
Summary of the invention
The present invention is directed to two CCD camera measure system, proposes a kind of new stated accuracy evaluation method, this method is in three-dimensional
The distance between measurement point and ideal point are calculated in space, evaluation method is more reasonable；Meanwhile the measurement for binocular structure
System, most of matching algorithms all need to determine whether polar curve calculates quasi- by epipolar line restriction, the accuracy that basis matrix calculates
Really, the method for the present invention also evaluates basis matrix, provides safeguard for the matching process of subsequent biocular systems.The present invention couple
The stated accuracy evaluation of binocular vision detection system is more accurate, has wide applicability.
Technical solution is as follows:
The method that the calibration result of a kind of pair of two CCD camera measure system is evaluated, calibration result include:
Left camera Intrinsic Matrix
Right camera Intrinsic Matrix
Wherein, fxl, fylFor the scale factor of left camera x-axis and y-axis direction, (u0l, v0l) it is principal point coordinate；fxr, fyrFor
The scale factor of right camera x-axis and y-axis direction, (u0r, v0r) it is principal point coordinate；
Spin matrix of the right camera coordinates system to left camera coordinates systemTranslation matrix Tc=[t1
t2 t3]T；Spin matrix of the left camera coordinates system to right camera coordinates systemTranslation matrix
Under difference calibration pose, coordinate (X of each mark point under world coordinate system in scaling boardij, Yij, Zij), i=
1,2,3 ... m, m are the numbers for demarcating pose；J=1,2,3 ... n, n are the number of mark point in scaling board；
Transformational relation [the R of left camera coordinates system or right camera coordinates system and world coordinate systemwi Twi], i=1,2,3 ...
m；
Above-mentioned calibration result is evaluated in accordance with the following steps:
Step 1, each mark point in scaling board image is calculated to sit in left camera image coordinate system and right camera image respectively
Two-dimensional coordinate under mark system；
Wherein, two-dimensional coordinate of the single marking point under left and right camera image coordinate system is denoted as:Wherein: subscript l represents what left camera obtained
Image, subscript r represent the image that right camera obtains, and subscript p represents p point；
Step 2, single marking point is calculated separately in the three-dimensional coordinate of left camera coordinates system
Wherein,
Step 3, the three-dimensional coordinate by mark point calculated in step 2 under left camera coordinates systemIt is transformed into world coordinate system, obtains its 3 d space coordinate pj'=[xj yj zj]T:
Step 4, the mark point 3 d space coordinate p obtained in step 3 is calculatedj'=[xj yj zj]TIn calibration result
Coordinate (X of the correspondence markings point under world coordinate systemij, Yij, Zij) between Euclidean distance dij；
Step 5, for based on the scaling board image obtained at scaling board and camera difference relative position repeat step 1~
Step 4, Calculation Estimation parameter ep；
Wherein w is the summation of the mark point quantity in all scaling board images used in as above calculating；
Work as epWhen less than preset threshold k, then calibration result is accurate, conversely, calibration result is inaccurate.
Further, when utilizing the relationship between right camera coordinates system and world coordinate system, step 2 is replaced with into step
2), step 3 replaces with step 3)；
Step 2) calculates single marking point in the three-dimensional coordinate of right camera coordinates system
Wherein,
Step 3), by three-dimensional coordinate of the mark point calculated in step 2) under right camera coordinates systemIt is transformed into world coordinate system, obtains its 3 d space coordinate pj'=[xj yj zj]T:
Further, to the evaluation method of basis matrix, steps are as follows:
According to calibration result, basis matrix F is calculated:
F=Ar -TEAl -1
For the coordinate of mark point in left camera image coordinate systemCalculate its polar curve I:
I=Fpjl
Wherein E is eigenmatrix, E=Tc×Rc；
Calculate corresponding same place in right camera imageTo the distance of polar curve I
H, when h is less than given threshold s, then the calculating of basis matrix F is accurate, conversely, the calculating mistake of basis matrix F.
The above-mentioned evaluation method to basis matrix can also use following steps:
According to calibration result, basis matrix F is calculated:
F=Al -TEAr -1
For the coordinate of mark point in right camera image coordinate systemCalculate its correspondence
Polar curve I:
I=Fpjr
Wherein E is eigenmatrix,
Calculate corresponding same place in left camera image coordinate systemTo polar curve I
Distance h, when h be less than given threshold s when, then the calculating of basis matrix F is accurate, conversely, the calculating mistake of basis matrix F.
Wherein, fundamental matrix embodies the inherent projective geometry relationship of two view geometries, and fundamental matrix only depends on camera shooting
The internal reference of machine and outer ginseng；
Eigenmatrix reflects the picture point of spatial point in the relationship under different perspectives camera between camera coordinates system, includes
The rotation of two cameras, translation information in physical space.
Further, scaling board image is the image obtained in calibration process or the calibrated left and right phase of utilization in step 1
The image that machine obtains.
Further, the calibration pose includes the position of binocular vision system shooting scaling board, angle；
It is preferred that number of the step 5 based on the uncalibrated image obtained at scaling board and camera difference relative position is 10
~30.
Further, the calibration result is the calibration result that Zhang Shi scaling method obtains, and scaling board is with concentric circles for spy
The plane reference plate of sign.
The method of the present invention can evaluate the inside and outside parameter and basis matrix that two CCD camera measure system calibrates, compared to
The method of traditional back projection evaluation calibration result, the method for the present invention are the measured values for calculating mark point in three-dimensional space
And the deviation of theoretical value, evaluation is more accurate, meanwhile, the present invention can determine whether the polar curve solved by basis matrix is accurate,
Reference is provided for subsequent homotopy mapping and three-dimensional measurement.
Specific embodiment
Technical solution of the present invention is described in detail below in conjunction with specific embodiment.
Two CCD camera measure system position is fixed, according to camera focus, multiple calibration poses is set, different marks are shot
It positions the plane reference plate image characterized by circle at appearance and stores；It include 695 round features in single scaling board；
In one embodiment of the invention, left and right camera focus is 40mm, and it is as follows that different calibration poses are arranged:
At working distance 900mm, the scaling board of face two CCD camera measure system is distinguished: 30 ° of inclination, downwards upwards
Inclination 30 °, be tilted to the left 30 °, be tilted to the right 30 °, as 8~pose of pose 11；Two CCD camera measure system is corresponding to shoot this
The scaling board image of the calibration pose of four groups of differing tilt angles；
At working distance 900mm, the scaling board of face two CCD camera measure system is rotated clockwise 90 °, then respectively to
It is upper inclination 30 °, tilt down 30 °, be tilted to the left 30 °, be tilted to the right 30 °, as 12~pose of pose 15；
The calibration result obtained using Zhang Shi scaling method is as follows:
Left camera Intrinsic Matrix
Right camera Intrinsic Matrix
Spin matrix of the right camera coordinates system to left camera coordinates systemTranslation matrix Tc=[t1
t2 t3]T；
Under difference calibration pose, coordinate (X of each mark point under world coordinate system in scaling boardij, Yij, Zij), i=
1,2,3 ... m, m are the numbers for demarcating pose；J=1,2,3 ... n, n are the number of mark point in scaling board；
Transformational relation [the R of left camera coordinates system or right camera coordinates system and world coordinate systemwiTwi], i=1,2,3 ... m；
Above-mentioned calibration result is evaluated in accordance with the following steps:
Step 1, calculate pose 1 scaling board image in each mark point respectively in left camera image coordinate system and right phase
Two-dimensional coordinate under machine image coordinate system；
Wherein, two-dimensional coordinate of the single marking point under left and right camera image coordinate system is denoted as:Wherein: subscript l represents what left camera obtained
Image, subscript r represent the image that right camera obtains, and subscript p represents p point；
Step 2, single marking point is calculated separately in the three-dimensional coordinate of left camera coordinates system
Wherein,
Step 3, the three-dimensional coordinate by mark point calculated in step 2 under left camera coordinates systemIt is transformed into world coordinate system, obtains its 3 d space coordinate pj'=[xj yj zj]T:
Step 2 can also calculate three-dimensional coordinate of the mark point under right camera coordinates system in 3 And by pjIt is transformed into world coordinate system；
Step 4, the mark point 3 d space coordinate p obtained in step 3 is calculatedj'=[xj yj zj]TIn calibration result
Coordinate (X of the correspondence markings point under world coordinate systemij, Yij, Zij) between Euclidean distance dij；
Step 5, for the scaling board image stored under each pose in 2~pose of pose 13, be repeated in step 1~
Step 4, Calculation Estimation parameter ep；
Wherein w is the summation of the mark point quantity in all scaling board images used in as above calculating；
Work as epWhen less than preset threshold k, then calibration result is accurate, conversely, calibration result is inaccurate.
Euclidean distance d according to each mark point under the single pose being calculatedijMean value, draw line chart, dij
Mean value computation the result is as follows:
| Pose 1 | Pose 2 | Pose 3 | Pose 4 | Pose 5 | Pose 6 | Pose 7 | Pose 8 | |
| dijMean value | 0.014 | 0.016 | 0.016 | 0.016 | 0.015 | 0.018 | 0.018 | 0.014 |
| Pose 9 | Pose 10 | Pose 11 | Pose 12 | Pose 13 | Pose 14 | Pose 15 | ||
| dijMean value | 0.013 | 0.014 | 0.016 | 0.018 | 0.019 | 0.016 | 0.015 |
Meanwhile evaluating to the basis matrix in two CCD camera measure system matching process, steps are as follows:
According to calibration result, basis matrix F is calculated:
F=Ar -TEAl -1
For the coordinate of mark point in left camera image coordinate systemCalculate polar curve I:
I=Fpjl
Wherein E is eigenmatrix, E=T' × R'；
Calculate corresponding same place in right camera image coordinate systemTo polar curve I
Distance h, when h be less than given threshold s when, then the calculating of basis matrix F is accurate, conversely, the calculating mistake of basis matrix F.
The h value obtained is counted according to label each under single pose and draws line chart, and h calculated result is as follows:
| Pose 1 | Pose 2 | Pose 3 | Pose 4 | Pose 5 | Pose 6 | Pose 7 | Pose 8 | |
| H value | 0.033 | 0.039 | 0.034 | 0.031 | 0.039 | 0.022 | 0.030 | 0.028 |
| Pose 9 | Pose 10 | Pose 11 | Pose 12 | Pose 13 | Pose 14 | Pose 15 | ||
| H value | 0.028 | 0.038 | 0.033 | 0.038 | 0.033 | 0.052 | 0.030 |
For ease of explanation and precise definition of the appended claims, term " on ", "lower", " left side " and " right side " are Q-characters
The description for the illustrative embodiments set.
The description that specific exemplary embodiment of the present invention is presented in front is for the purpose of illustration and description.Before
The description in face is not intended to become without missing, is not intended to limit the invention to disclosed precise forms, shows
So, much change according to the above instruction and variation is all possible.It selects exemplary implementation scheme and is described to be to understand
Certain principles and practical application of the invention are released, so that others skilled in the art can be realized and utilize this
The various exemplary implementation schemes of invention and its different selection forms and modification.The scope of the present invention is intended to by appended power
Sharp claim and its equivalent form are limited.
Claims (7)
1. the method that the calibration result of a kind of pair of two CCD camera measure system is evaluated, calibration result include:
Left camera Intrinsic Matrix
Right camera Intrinsic Matrix
Spin matrix of the right camera coordinates system to left camera coordinates systemTranslation matrix Tc=[t1 t2 t3]T；
Spin matrix of the left camera coordinates system to right camera coordinates systemTranslation matrix T`c=[t`1 t`2
t`3]T；
Under difference calibration pose, coordinate (X of each mark point under world coordinate system in scaling boardij, Yij, Zij), i=1,2,
3 ... m, m are the numbers for demarcating pose；J=1,2,3 ... n, n are the number of mark point in scaling board；
Transformational relation [the R of left camera coordinates system or right camera coordinates system and world coordinate systemwi Twi], i=1,2,3 ... m；
It is characterized in that, being evaluated in accordance with the following steps above-mentioned calibration result:
Step 1, calculate scaling board image in each mark point respectively in left camera image coordinate system and right camera image coordinate system
Under two-dimensional coordinate；
Wherein, two-dimensional coordinate of the single marking point under left and right camera image coordinate system is denoted as:Wherein: subscript l represents the figure that left camera obtains
Picture, subscript r represent the image that right camera obtains, and subscript p represents p point；
Step 2, single marking point is calculated separately in the three-dimensional coordinate of left camera coordinates system
Wherein,
Step 3, the three-dimensional coordinate by mark point calculated in step 2 under left camera coordinates systemIt is transformed into world coordinate system, obtains its 3 d space coordinate pj'=[xj yj zj]T:
Step 4, the mark point 3 d space coordinate p obtained in step 3 is calculatedj'=[xj yj zj]TMark corresponding with calibration result
Coordinate (X of the note point under world coordinate systemij, Yij, Zij) between Euclidean distance dij；
Step 5, for repeating step 1~step 4 based on the scaling board image obtained at scaling board and camera difference relative position,
Calculation Estimation parameter ep；
Wherein w is the summation of the mark point quantity in all scaling board images used in as above calculating；
Work as epWhen less than preset threshold k, then calibration result is accurate, conversely, calibration result is inaccurate.
2. the method evaluated as described in claim 1 the calibration result of two CCD camera measure system, it is characterised in that: step
Rapid 2 replace with step 2), and step 3 replaces with step 3),
Step 2) calculates single marking point in the three-dimensional coordinate of right camera coordinates system
Wherein,
Step 3), by three-dimensional coordinate of the mark point calculated in step 2) under right camera coordinates systemIt is transformed into world coordinate system, obtains its 3 d space coordinate pj'=[xj yj zj]T:
3. the method evaluated as claimed in claim 1 or 2 the calibration result of two CCD camera measure system, feature exist
In: according to calibration result, calculate basis matrix F:
F=Ar -TEAl -1
For the coordinate of mark point in left camera image coordinate systemCalculate its polar curve I:
I=Fpjl
Wherein E is eigenmatrix, E=Tc×Rc；
Calculate corresponding same place in right camera image coordinate systemTo polar curve I away from
From h, when h is less than given threshold s, then the calculating of basis matrix F is accurate, conversely, the calculating mistake of basis matrix F.
4. the method evaluated as claimed in claim 1 or 2 the calibration result of two CCD camera measure system, feature exist
In: according to calibration result, calculate basis matrix F:
F=Al -TEAr -1
For the coordinate of mark point in right camera image coordinate systemIt calculates it and corresponds to polar curve
I:
I=Fpjr
Wherein E is eigenmatrix, E=T`c×R`c；
Calculate corresponding same place in left camera image coordinate systemTo the distance of polar curve I
H, when h is less than given threshold s, then the calculating of basis matrix F is accurate, conversely, the calculating mistake of basis matrix F.
5. the method evaluated as claimed in claim 1 or 2 the calibration result of two CCD camera measure system, feature exist
In: scaling board image is the image obtained in calibration process or the image for utilizing calibrated left and right camera acquisition in step 1.
6. the method evaluated as claimed in claim 1 or 2 the calibration result of two CCD camera measure system, feature exist
In: the step 5 is 10~30 based on the uncalibrated image number obtained at scaling board and camera difference relative position.
7. the method evaluated as claimed in claim 1 or 2 the calibration result of two CCD camera measure system, feature exist
In: the calibration result is the calibration result that Zhang Shi scaling method obtains, and scaling board is the plane reference characterized by concentric circles
Plate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811232049.4A CN109522935B (en) | 2018-10-22 | 2018-10-22 | Method for evaluating calibration result of binocular vision measurement system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811232049.4A CN109522935B (en) | 2018-10-22 | 2018-10-22 | Method for evaluating calibration result of binocular vision measurement system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109522935A true CN109522935A (en) | 2019-03-26 |
| CN109522935B CN109522935B (en) | 2021-07-02 |
Family
ID=65772226
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811232049.4A Active CN109522935B (en) | 2018-10-22 | 2018-10-22 | Method for evaluating calibration result of binocular vision measurement system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109522935B (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110009676A (en) * | 2019-04-11 | 2019-07-12 | 电子科技大学 | A kind of intrinsic properties decomposition method of binocular image |
| CN110728709A (en) * | 2019-10-16 | 2020-01-24 | 广州中科智巡科技有限公司 | Intelligent switch identification system and method based on binocular vision technology |
| CN110827361A (en) * | 2019-11-01 | 2020-02-21 | 清华大学 | Camera group calibration method and device based on global calibration frame |
| CN111210480A (en) * | 2020-01-06 | 2020-05-29 | 中国农业大学 | Binocular precision detection method, system, equipment and storage medium |
| CN111768448A (en) * | 2019-03-30 | 2020-10-13 | 北京伟景智能科技有限公司 | Spatial coordinate system calibration method based on multi-camera detection |
| CN111784771A (en) * | 2020-06-28 | 2020-10-16 | 北京理工大学 | 3D triangulation method and device based on binocular camera |
| CN112308926A (en) * | 2020-10-16 | 2021-02-02 | 易思维（杭州）科技有限公司 | Camera external reference calibration method without public view field |
| CN112330755A (en) * | 2020-11-26 | 2021-02-05 | 展讯通信（上海）有限公司 | Calibration evaluation method and device of all-round system, storage medium and terminal |
| CN112489122A (en) * | 2020-10-20 | 2021-03-12 | 江苏集萃未来城市应用技术研究所有限公司 | Method for determining GNSS coordinates of shielding electronic boundary point based on binocular camera |
| CN112734858A (en) * | 2021-01-08 | 2021-04-30 | 长沙行深智能科技有限公司 | Binocular calibration precision online detection method and device |
| CN112907676A (en) * | 2019-11-19 | 2021-06-04 | 浙江商汤科技开发有限公司 | Calibration method, device and system of sensor, vehicle, equipment and storage medium |
| CN113052918A (en) * | 2021-04-23 | 2021-06-29 | 北京机械设备研究所 | Method, device, medium and equipment for evaluating calibration error of antipodal binocular camera |
| CN113624371A (en) * | 2021-08-06 | 2021-11-09 | 中国科学院自动化研究所 | High-resolution visual touch sensor based on binocular vision and point cloud generation method |
| CN117414129A (en) * | 2023-12-18 | 2024-01-19 | 吉林大学第一医院 | System and method for measuring spinal activity |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102107179A (en) * | 2010-12-14 | 2011-06-29 | 浙江工业大学 | Method for controlling single-layer leather gluing based on binocular vision |
| CN103247053A (en) * | 2013-05-16 | 2013-08-14 | 大连理工大学 | Accurate part positioning method based on binocular microscopy stereo vision |
| US8897502B2 (en) * | 2011-04-29 | 2014-11-25 | Aptina Imaging Corporation | Calibration for stereoscopic capture system |
| CN105005999A (en) * | 2015-08-12 | 2015-10-28 | 北京航空航天大学 | Obstacle detection method for blind guiding instrument based on computer stereo vision |
| CN105678709A (en) * | 2016-01-12 | 2016-06-15 | 西安交通大学 | LED handheld target optical center offset correction algorithm |
-
2018
- 2018-10-22 CN CN201811232049.4A patent/CN109522935B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102107179A (en) * | 2010-12-14 | 2011-06-29 | 浙江工业大学 | Method for controlling single-layer leather gluing based on binocular vision |
| US8897502B2 (en) * | 2011-04-29 | 2014-11-25 | Aptina Imaging Corporation | Calibration for stereoscopic capture system |
| CN103247053A (en) * | 2013-05-16 | 2013-08-14 | 大连理工大学 | Accurate part positioning method based on binocular microscopy stereo vision |
| CN105005999A (en) * | 2015-08-12 | 2015-10-28 | 北京航空航天大学 | Obstacle detection method for blind guiding instrument based on computer stereo vision |
| CN105678709A (en) * | 2016-01-12 | 2016-06-15 | 西安交通大学 | LED handheld target optical center offset correction algorithm |
Non-Patent Citations (3)
| Title |
|---|
| OLEKSANDR SEMENIUTA: "Analysis of Camera Calibration with Respect to Measurement Accuracy", 《 48TH CIRP INTERNATIONAL CONFERENCE ON MANUFACTURING SYSTEMS (CIRP CMS)》 * |
| XINXING SHAO ET AL.: "Experimental investigation of strain errors in stereo-digital image correlation due to camera calibration", 《OPTICAL ENGINEERING》 * |
| 李丽军: "基于机器人双目立体视觉的三维重建", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111768448A (en) * | 2019-03-30 | 2020-10-13 | 北京伟景智能科技有限公司 | Spatial coordinate system calibration method based on multi-camera detection |
| CN110009676B (en) * | 2019-04-11 | 2019-12-17 | 电子科技大学 | Intrinsic property decomposition method of binocular image |
| CN110009676A (en) * | 2019-04-11 | 2019-07-12 | 电子科技大学 | A kind of intrinsic properties decomposition method of binocular image |
| CN110728709A (en) * | 2019-10-16 | 2020-01-24 | 广州中科智巡科技有限公司 | Intelligent switch identification system and method based on binocular vision technology |
| CN110728709B (en) * | 2019-10-16 | 2022-08-16 | 广州中科智巡科技有限公司 | Intelligent switch identification system and method based on binocular vision technology |
| CN110827361A (en) * | 2019-11-01 | 2020-02-21 | 清华大学 | Camera group calibration method and device based on global calibration frame |
| CN112907676A (en) * | 2019-11-19 | 2021-06-04 | 浙江商汤科技开发有限公司 | Calibration method, device and system of sensor, vehicle, equipment and storage medium |
| CN111210480A (en) * | 2020-01-06 | 2020-05-29 | 中国农业大学 | Binocular precision detection method, system, equipment and storage medium |
| CN111210480B (en) * | 2020-01-06 | 2023-08-22 | 中国农业大学 | Binocular precision detection method, binocular precision detection system, binocular precision detection equipment and storage medium |
| CN111784771A (en) * | 2020-06-28 | 2020-10-16 | 北京理工大学 | 3D triangulation method and device based on binocular camera |
| CN111784771B (en) * | 2020-06-28 | 2023-05-23 | 北京理工大学 | Binocular camera-based 3D triangulation method and device |
| CN112308926B (en) * | 2020-10-16 | 2023-03-31 | 易思维（杭州）科技有限公司 | Camera external reference calibration method without public view field |
| CN112308926A (en) * | 2020-10-16 | 2021-02-02 | 易思维（杭州）科技有限公司 | Camera external reference calibration method without public view field |
| CN112489122B (en) * | 2020-10-20 | 2022-08-23 | 江苏集萃未来城市应用技术研究所有限公司 | Method for determining GNSS coordinates of shielding electronic boundary point based on binocular camera |
| CN112489122A (en) * | 2020-10-20 | 2021-03-12 | 江苏集萃未来城市应用技术研究所有限公司 | Method for determining GNSS coordinates of shielding electronic boundary point based on binocular camera |
| CN112330755A (en) * | 2020-11-26 | 2021-02-05 | 展讯通信（上海）有限公司 | Calibration evaluation method and device of all-round system, storage medium and terminal |
| CN112734858B (en) * | 2021-01-08 | 2022-11-29 | 长沙行深智能科技有限公司 | Binocular calibration precision online detection method and device |
| CN112734858A (en) * | 2021-01-08 | 2021-04-30 | 长沙行深智能科技有限公司 | Binocular calibration precision online detection method and device |
| CN113052918A (en) * | 2021-04-23 | 2021-06-29 | 北京机械设备研究所 | Method, device, medium and equipment for evaluating calibration error of antipodal binocular camera |
| CN113624371A (en) * | 2021-08-06 | 2021-11-09 | 中国科学院自动化研究所 | High-resolution visual touch sensor based on binocular vision and point cloud generation method |
| CN117414129A (en) * | 2023-12-18 | 2024-01-19 | 吉林大学第一医院 | System and method for measuring spinal activity |
| CN117414129B (en) * | 2023-12-18 | 2024-03-08 | 吉林大学第一医院 | System and method for measuring spinal activity |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109522935B (en) | 2021-07-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109522935A (en) | The method that the calibration result of a kind of pair of two CCD camera measure system is evaluated | |
| CN109029257B (en) | Large-scale workpiece pose measurement system and method based on stereoscopic vision and structured light vision | |
| CN106651942B (en) | Three-dimensional rotating detection and rotary shaft localization method based on characteristic point | |
| CN106683173B (en) | A method of Three-dimensional Gravity is improved based on neighborhood Block- matching and is laid foundations the dense degree of cloud | |
| Strobl et al. | More accurate pinhole camera calibration with imperfect planar target | |
| CN111243002A (en) | Monocular laser speckle projection system calibration and depth estimation method applied to high-precision three-dimensional measurement | |
| CN110285827B (en) | Distance-constrained photogrammetry high-precision target positioning method | |
| CN108510551B (en) | Method and system for calibrating camera parameters under long-distance large-field-of-view condition | |
| US20080243416A1 (en) | Global calibration for stereo vision probe | |
| CN110728715A (en) | Camera angle self-adaptive adjusting method of intelligent inspection robot | |
| CN109272574B (en) | Construction method and calibration method of linear array rotary scanning camera imaging model based on projection transformation | |
| CN107424196B (en) | Stereo matching method, device and system based on weak calibration multi-view camera | |
| CN105378794A (en) | 3d recording device, method for producing 3d image, and method for setting up 3d recording device | |
| CN113240740B (en) | Attitude measurement method based on phase-guided binocular vision dense marking point matching | |
| JP4234059B2 (en) | Camera calibration method and camera calibration apparatus | |
| CN110763204B (en) | Planar coding target and pose measurement method thereof | |
| CN106709955B (en) | Space coordinate system calibration system and method based on binocular stereo vision | |
| CN109272555B (en) | External parameter obtaining and calibrating method for RGB-D camera | |
| CN110044301B (en) | Three-dimensional point cloud computing method based on monocular and binocular mixed measurement | |
| US11295478B2 (en) | Stereo camera calibration method and image processing device for stereo camera | |
| WO2023201578A1 (en) | Extrinsic parameter calibration method and device for monocular laser speckle projection system | |
| CN116740187A (en) | Multi-camera combined calibration method without overlapping view fields | |
| CN112164119A (en) | Calibration method of system with multiple cameras placed in surrounding mode and suitable for narrow space | |
| Li et al. | An automatic laser scanning system for accurate 3D reconstruction of indoor scenes | |
| JP7033294B2 (en) | Imaging system, imaging method |
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 | ||
| CP01 | Change in the name or title of a patent holder |
Address after: Room 495, building 3, 1197 Bin'an Road, Binjiang District, Hangzhou City, Zhejiang Province 310051 Patentee after: Yi Si Si (Hangzhou) Technology Co.,Ltd. Address before: Room 495, building 3, 1197 Bin'an Road, Binjiang District, Hangzhou City, Zhejiang Province 310051 Patentee before: ISVISION (HANGZHOU) TECHNOLOGY Co.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder |