CN112634373B - Visual measurement system dynamic correction method based on zero-expansion ceramic calibration plate - Google Patents
Visual measurement system dynamic correction method based on zero-expansion ceramic calibration plate Download PDFInfo
- Publication number
- CN112634373B CN112634373B CN202011382690.3A CN202011382690A CN112634373B CN 112634373 B CN112634373 B CN 112634373B CN 202011382690 A CN202011382690 A CN 202011382690A CN 112634373 B CN112634373 B CN 112634373B
- Authority
- CN
- China
- Prior art keywords
- zero
- calibration plate
- expansion ceramic
- measurement system
- camera
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M9/00—Aerodynamic testing; Arrangements in or on wind tunnels
- G01M9/06—Measuring arrangements specially adapted for aerodynamic testing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E30/00—Energy generation of nuclear origin
- Y02E30/30—Nuclear fission reactors
Abstract
The invention provides a visual measurement system correction method based on a zero-expansion ceramic calibration plate, which can overcome the influence of high-low temperature change and transmission path air flow density change on measurement accuracy in the test process. Placing a zero-expansion ceramic calibration plate in a measured view field space of the vision measurement system, wherein a target point is arranged on the zero-expansion ceramic calibration plate; during measurement, each camera in the vision measurement system performs real-time image acquisition, extracts image coordinates of each target point on the zero-expansion ceramic calibration plate, calculates a re-projection error e, and performs parameter correction when the e is larger than a preset threshold value s; the parameter correction process comprises the following steps: firstly, establishing a relation between a true value and a predicted value of each target point on a zero-expansion ceramic calibration plate, and further obtaining a distortion correction model; and then inputting the directly calculated measurement point space relative coordinates under the static parameter calibration condition of the vision measurement system into a distortion correction model for calculation, wherein the output value is the distortion corrected measurement point space three-dimensional coordinates.
Description
Technical Field
The invention relates to a correction method, in particular to a vision measurement system dynamic correction method based on a zero-expansion ceramic calibration plate.
Background
The stereoscopic vision measurement technology is realized based on the parallax principle, a plurality of cameras with known spatial position and posture relations (one of the cameras is a reference camera, and the spatial position and posture relations of other cameras relative to the reference camera are known) are utilized to simultaneously acquire images of the measured features in different directions, and the corresponding homonymous image point pairs of the measured features are acquired through technologies such as image processing, homonymous point matching and the like; and then, an imaging light equation is established by using a camera imaging model, a light triangle intersection constraint is established, a multi-vision measurement mathematical model is established, and then, the three-dimensional coordinates of the measured feature space are calculated.
In the vision measurement system, the spatial conversion relation (i.e. the external parameters of the camera) among the multi-camera coordinate systems and each camera distortion parameter (i.e. the internal parameters of the camera) are the prior conditions which must be known in the process of resolving the stereo vision measurement model, and the prior calibration and orientation are needed Techniques for And acquiring the internal and external parameters of the camera.
The camera calibration internal parameters comprise internal azimuth parameters of the camera and various lens distortions. The internal azimuth parameters of the camera comprise the principal point coordinates and the principal distance (i.e. focal length) of the camera; lens distortion refers to the point location error of an image point from its ideal position caused by the design, manufacture and equipment of a camera objective system, and includes a radial distortion coefficient, an eccentric distortion coefficient and an area array distortion coefficient.
The out-of-camera parameters include three-dimensional translation parameters (T x ，T y ，T z ) And three-directional rotation parameter (θ x ，θ y ，θ z )。
However, in some special occasions, such as wind tunnel tests, the environment is dynamically changed in the measuring process, the temperature change of wind tunnel airflow is large, the temperature gradient of a gaseous medium can influence the transmission path of light, and the airflow density can refract and distort the optical path along with the change of temperature and flow velocity; the method for static calibration and dynamic measurement of the traditional vision measurement system is not applicable any more, and the vision measurement system parameters calibrated under the static condition only comprise the internal and external parameters of the camera and the distortion parameters of the optical system; the change of the environmental air flow in the test can introduce new distortion, and dynamic correction is needed; but the distortion caused by the environment does not conform to the conventional lens distortion model.
Disclosure of Invention
In view of the above, the invention provides a dynamic correction method of a vision measurement system based on a zero-expansion ceramic calibration plate, which is applied to the dynamic correction of distortion of the vision measurement system in special environments such as wind tunnel test and the like, and can overcome the influence of high-low temperature change and transmission path air flow density change on measurement accuracy in the test process.
The vision measurement system dynamic correction method based on the zero-expansion ceramic calibration plate comprises the following steps:
placing a zero-expansion ceramic calibration plate in a measured view field space of the vision measurement system, wherein more than four circular targets are arranged on the zero-expansion ceramic calibration plate;
firstly, calibrating static parameters of the vision measurement system, including calibration of internal parameters and external parameters, so as to determine an internal parameter matrix of each camera, a distortion model of each camera and an external parameter matrix of each camera relative to a reference camera in the vision measurement system;
during measurement, each camera in the vision measurement system performs real-time image acquisition, the image coordinates of each target point on the zero-expansion ceramic calibration plate are extracted through the images of the zero-expansion ceramic calibration plate in the measured view field space acquired by each camera, and then the re-projection error e of the target point in the images acquired by each non-reference camera relative to the reference camera is calculated; if e > s, indicating that parameter correction is needed, if e is less than or equal to s, parameter correction is not needed; s is a preset re-projection error threshold;
the parameter correction process comprises the following steps:
the space relative coordinates of each target point on the zero-expansion ceramic calibration plate are known standard values and are true values; the space relative coordinates of each target point measured by the vision measurement system under static parameter calibration adjustment are used as predicted values, and the relation between the real values and the predicted values of each target point on the zero-expansion ceramic calibration plate is established, so that a distortion correction model is obtained;
aiming at the image pair with the re-projection error exceeding the preset re-projection error threshold and needing parameter correction, the measurement point space relative coordinates directly calculated under the static parameter calibration condition of the vision measurement system are input into the distortion correction model for calculation, and the output value is the measurement point space three-dimensional coordinates after distortion correction.
As a preferred mode of the present invention: when the neural network is built, the spatial relative coordinates measured under the static parameter calibration condition of each target point are taken as input data samples, the known standard value of each spatial relative coordinate is taken as output data samples, and the network is optimized and trained to obtain the distortion correction model.
As a preferred mode of the present invention: the re-projection error e is calculated by the following formula:
wherein: e, e x The re-projection error of row coordinates in a camera image coordinate system; e, e y Re-projection errors of column coordinates in a camera image coordinate system; x is the row coordinate of the target point in the non-reference camera image; y is the column coordinate of the target point in the non-reference camera image; f is the focal length of the non-reference camera; x, Y, Z is the three-dimensional coordinate of the target point calculated by the vision measurement system under the space coordinate system; x is X S 、Y S 、Z S The three-dimensional coordinate true value of the target point under the space coordinate system; x is x 0 And y 0 The main point coordinates of a reference camera in the vision measurement system; r is (r) 1 To r 9 The parameters of the rotation matrix in the outer parameters are respectively.
As a preferred mode of the present invention: the flatness of the zero-expansion ceramic calibration plate is superior to 10 -2 Delta, the position degree and the roundness of the target point on the zero-expansion ceramic calibration plate are superior to 10 -2 δ, wherein δ is the maximum value of the measurement error of the vision measurement system.
As a preferred mode of the present invention: and placing more than two zero-expansion ceramic calibration plates in the measured view field space, wherein the zero-expansion ceramic calibration plates are arranged around the measured object.
As a preferred mode of the present invention: the targets on the zero-expansion ceramic calibration plate are arranged in a square matrix.
As a preferred mode of the present invention: the formation mode of the target spot on the zero-expansion ceramic calibration plate is as follows: processing a blind hole on the reference surface of the zero-expansion ceramic calibration plate; then placing a filling cylinder in each blind hole, wherein the filling cylinder is in interference fit with the blind hole; the zero-expansion ceramic calibration plate is white in matrix color, and the filling cylinder is dark or black in color, so that a target point is formed.
The beneficial effects are that:
(1) The invention adopts the zero expansion calibration plate to dynamically correct distortion of the vision measurement system in the wind tunnel measurement test, provides stable and reliable physical standard through the zero expansion calibration plate, and can overcome the influence of environmental factors such as high and low temperature change, air flow disturbance and the like on the wind tunnel on the vision measurement system.
(2) According to the invention, the distortion correction model is constructed by adopting a neural network mode, so that the influence of the parameterized model on the measurement result is reduced, the distortion correction of the wind tunnel vision measurement system is realized, and the measurement accuracy of the vision system in severe environments such as high-low temperature change, airflow fluctuation and the like is improved.
Drawings
FIG. 1 is a flow chart of a calibration method of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples.
The embodiment provides a vision measurement system dynamic correction method based on a zero-expansion ceramic calibration plate, which is applied to parameter optimization of a vision measurement system in a special wind tunnel test environment.
The vision measurement system is installed outside the wind tunnel observation window, measures the interior testee of wind tunnel through the observation window, and the vision measurement system includes: the system comprises two cameras, a lens, an image acquisition computer and a cable; the range shown by the dotted line in the figure is the measurable area of the vision measurement system, and the object to be measured is positioned at the wind tunnel air outlet.
By adopting the squareFirstly, preparing a zero expansion calibration plate: the zero expansion ceramic calibration plate adopts near zero expansion ceramic matrix composite material, the material is prepared by compounding negative expansion material and positive expansion material according to proper proportion and process, the prepared thermal expansion coefficient of the near zero expansion material is controllable, and the thermal expansion coefficient of the material is about 1 multiplied by 10 in the range of normal temperature to 1000 ℃ due to the low thermal expansion coefficient of the material when the material is subjected to large temperature gradient change, the overall size change is small -6 /K。
The zero-expansion ceramic calibration plate is of a planar structure, and the planeness is better than 10 -2 The delta, set up the circular target spot on the calibration board, the target spot is square matrix arrangement, the target spot number is 25 or 49, the target spot position degree and roundness are better than 10 -2 Delta, where delta is the measurement error requirement (i.e., the maximum value of the measurement error) of the vision measurement system. For example, the measurement error of the vision measurement system is required to be smaller than 1mm, namely the measurement error is required to be 1mm, the flatness of the calibration plate is required to be better than 0.01mm, and the target spot position degree and roundness are both better than 0.01mm. The target spot can be installed by processing a blind hole array on the reference surface of the calibration plate, and then processing a filling cylinder, wherein the diameter tolerance of the filling cylinder is larger than the diameter of the blind hole, so that the filling cylinder is in interference fit with the blind hole; the color of the base body of the calibration plate is white, and the color of the filling cylinder is dark or black which is convenient to distinguish from the base body, so that a target point is formed.
Then erecting a vision measurement system and a prepared calibration plate on the wind tunnel test site: and placing the zero-expansion ceramic calibration plate in a measured field space in the wind tunnel, and placing 3 to 4 zero-expansion ceramic calibration plates under the condition of not shielding a measured object. In the example, the calibration plate is in the form of a 7×7 target array, and three zero-expansion ceramic calibration plates are arranged around the measured object.
As shown in fig. 1, the visual measurement system correction method based on the zero-expansion ceramic calibration plate comprises the following specific steps:
step one: calibrating static parameters of a vision measurement system:
before a vision measurement system is erected on a wind tunnel test site, firstly, calibrating static parameters of the vision measurement system, namely, calibrating internal parameters and external parameters of the vision measurement system under normal temperature and static conditions, thereby determining an internal parameter matrix of each camera, a distortion model of each camera and an external parameter matrix among multiple cameras in the vision measurement system (a reference camera is arranged, and the external parameter matrix among the multiple cameras refers to an external parameter matrix among cameras (non-reference cameras) except the reference camera and the reference camera in the vision measurement system);
taking a stereoscopic vision measurement system with two cameras as an example, making the two cameras be a left camera and a right camera respectively, and determining an internal parameter matrix M of the left camera by calibrating static parameters of the stereoscopic vision measurement system L Intrinsic matrix M of right camera R External parameter matrix M of two cameras LR A distortion model;
the left in-camera parameter matrix, the right in-camera parameter matrix and the outer parameter matrices of the two cameras can have various parameter forms, taking the following as an example:
wherein: f (f) L Is the focal length of the left camera, dx L Differentiating the row coordinate of the left camera, dy L To differentiate the left camera column coordinates, x 0L Coordinate for main point row of left camera, y 0L The coordinates of the main point column of the left camera;
f R is the focal length of the right camera, dx R To differentiate the right camera row coordinates dy R To differentiate the right camera column coordinates, x 0R Coordinate for main point row of right camera, y 0R The main point row coordinates of the right camera;
r 1 to r 9 Respectively the parameters of the rotation matrix in the external parameters of the camera, t x Is the respective parameter of the translation matrix among the out-of-camera parameters.
The distortion parameters caused by the camera optical system include: coefficient of radial distortion (k) 1 ，k 2 ) Eccentric distortion coefficient (p 1 ，p 2 ) And area array deformation coefficient(s) 1 ，s 2 ) The method comprises the steps of carrying out a first treatment on the surface of the The distortion model of the camera is as follows:
wherein: delta x Distortion in x direction, delta y The distortion in the y direction is referred to, x is referred to as row coordinates in the camera image coordinates, and y is referred to as column coordinates in the camera image coordinates;
step two: erecting a calibration plate on a wind tunnel test site: and placing the zero-expansion ceramic calibration plate in a measured field space in the wind tunnel, and placing 3 to 4 zero-expansion ceramic calibration plates under the condition of not shielding a measured object.
Step three: and (3) correction threshold judgment:
after the wind tunnel test starts, each camera in the vision measurement system performs real-time image acquisition, and the image coordinates of a target point on the calibration plate are extracted and obtained through the calibration plate images acquired by each camera, and the re-projection error e of each non-reference camera relative to the reference camera is calculated according to the following formula:
wherein: e, e x The re-projection error of row coordinates in a camera image coordinate system; e, e y Re-projection errors of column coordinates in a camera image coordinate system; x is the row coordinate of the target point in the non-reference camera image; y is the column coordinate of the target point in the non-reference camera image; f is the focal length of the non-reference camera; x, Y, Z is the three-dimensional coordinate of the target point calculated by the vision measurement system under the space coordinate system; x is X S 、Y S 、Z S The three-dimensional coordinate true value of the target point under the space coordinate system; x is x 0 And y 0 The main point coordinates of a reference camera in the vision measurement system;
setting a preset threshold value s to be 0.2 pixel, and if e > s, performing parameter correction flow (namely step four and step five), if e is less than or equal to s, then parameter correction is not needed.
Step four: establishing a distortion correction model through a neural network
The relation between the space relative coordinates of the target spots on the calibration plate and the space relative coordinates of each target spot predicted by the static model is established through a neural network, so that a distortion correction model is obtained, and the method is specific:
the space relative coordinates of each target point on the calibration plate are known standard values (namely true values); the image acquired by the camera in the vision measurement system can calculate the image coordinates of each target point, and the output value predicted by the static model, namely the space relative coordinates of each target point under the static parameter calibration adjustment, can be obtained according to the system parameters calibrated under the static condition;
let the standard value of the spatial relative coordinate of the ith target point be P bi (x bi ,y bi ,z bi ) The space relative coordinate measured under the static parameter calibration condition is P ji (x ji ,y ji ,z ji ) The method comprises the steps of carrying out a first treatment on the surface of the The difference between the real value and the static model predicted value is:
(δ xi ,δ yi ,δ zi )＝(x bi ,y bi ,z bi )-(x ji ,y ji ,z ji )
wherein delta xi 、δ yi 、δ zi The differences in three directions of the three-dimensional coordinate system are respectively.
Based on the method, a neural network model is constructed, the space relative coordinates measured under the static parameter calibration condition of each target point are taken as input data samples, the standard value of the space relative coordinates is taken as output data samples, and the model is optimized and trained to obtain a distortion correction model.
Step five: distortion correction:
and (3) inputting the coordinate of the measuring point directly calculated under the static parameter calibration condition of the vision measurement system into a distortion correction model for calculation aiming at the image pair which is acquired by the vision measurement system and needs distortion correction and exceeds the threshold value s, wherein the output value is the three-dimensional coordinate of the measuring point space after distortion correction.
While the invention has been described in detail in the foregoing general description and specific examples, it will be apparent to those skilled in the art that modifications and improvements can be made thereto. Accordingly, such modifications or improvements may be made without departing from the spirit of the invention and are intended to be within the scope of the invention as claimed.
Claims (7)
1. A vision measurement system dynamic correction method based on a zero-expansion ceramic calibration plate is characterized by comprising the following steps of:
placing a zero-expansion ceramic calibration plate in a measured view field space of the vision measurement system, wherein more than four circular targets are arranged on the zero-expansion ceramic calibration plate;
firstly, calibrating static parameters of the vision measurement system, including calibration of internal parameters and external parameters, so as to determine an internal parameter matrix of each camera, a distortion model of each camera and an external parameter matrix of each camera relative to a reference camera in the vision measurement system;
during measurement, each camera in the vision measurement system performs real-time image acquisition, the image coordinates of each target point on the zero-expansion ceramic calibration plate are extracted through the images of the zero-expansion ceramic calibration plate in the measured view field space acquired by each camera, and then the re-projection error e of the target point in the images acquired by each non-reference camera relative to the reference camera is calculated; if e > s, indicating that parameter correction is needed, if e is less than or equal to s, parameter correction is not needed; s is a preset re-projection error threshold;
the parameter correction process comprises the following steps:
the space relative coordinates of each target point on the zero-expansion ceramic calibration plate are known standard values and are true values; the space relative coordinates of each target point measured by the vision measurement system under static parameter calibration adjustment are used as predicted values, and the relation between the real values and the predicted values of each target point on the zero-expansion ceramic calibration plate is established, so that a distortion correction model is obtained;
aiming at the image pair with the re-projection error exceeding the preset re-projection error threshold and needing parameter correction, the measurement point space relative coordinates directly calculated under the static parameter calibration condition of the vision measurement system are input into the distortion correction model for calculation, and the output value is the measurement point space three-dimensional coordinates after distortion correction.
2. The visual measurement system dynamic correction method based on the zero-expansion ceramic calibration plate according to claim 1, wherein: when the neural network is built, the spatial relative coordinates measured under the static parameter calibration condition of each target point are taken as input data samples, the known standard value of each spatial relative coordinate is taken as output data samples, and the network is optimized and trained to obtain the distortion correction model.
3. The visual measurement system dynamic correction method based on the zero-expansion ceramic calibration plate according to claim 1 or 2, wherein: the re-projection error e is calculated by the following formula:
wherein: e, e x The re-projection error of row coordinates in a camera image coordinate system; e, e y Re-projection errors of column coordinates in a camera image coordinate system; x is the row coordinate of the target point in the non-reference camera image; y is the column coordinate of the target point in the non-reference camera image; f is the focal length of the non-reference camera; x, Y, Z is the three-dimensional coordinate of the target point calculated by the vision measurement system under the space coordinate system; x is X S 、Y S 、Z S The three-dimensional coordinate true value of the target point under the space coordinate system; x is x 0 And y 0 The main point coordinates of a reference camera in the vision measurement system; r is (r) 1 To r 9 Respectively obtaining parameters of a rotation matrix in the external parameters; delta x Distortion in x direction, delta y Refers to distortion in the y-direction.
4. The visual measurement system dynamic correction method based on the zero-expansion ceramic calibration plate according to claim 1 or 2, wherein: the flatness of the zero-expansion ceramic calibration plate is superior to 10 -2 Delta, the position degree and the roundness of the target point on the zero-expansion ceramic calibration plate are better than 10 -2 δ, wherein δ is the maximum value of the measurement error of the vision measurement system.
5. The visual measurement system dynamic correction method based on the zero-expansion ceramic calibration plate according to claim 1 or 2, wherein: and placing more than two zero-expansion ceramic calibration plates in the measured view field space, wherein the zero-expansion ceramic calibration plates are arranged around the measured object.
6. The visual measurement system dynamic correction method based on the zero-expansion ceramic calibration plate according to claim 1 or 2, wherein: the targets on the zero-expansion ceramic calibration plate are arranged in a square matrix.
7. The visual measurement system dynamic correction method based on the zero-expansion ceramic calibration plate according to claim 1 or 2, wherein: the formation mode of the target spot on the zero-expansion ceramic calibration plate is as follows: processing a blind hole on the reference surface of the zero-expansion ceramic calibration plate; then placing a filling cylinder in each blind hole, wherein the filling cylinder is in interference fit with the blind hole; the zero-expansion ceramic calibration plate is white in matrix color, and the filling cylinder is dark or black in color, so that a target point is formed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011382690.3A CN112634373B (en) | 2020-12-01 | 2020-12-01 | Visual measurement system dynamic correction method based on zero-expansion ceramic calibration plate |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011382690.3A CN112634373B (en) | 2020-12-01 | 2020-12-01 | Visual measurement system dynamic correction method based on zero-expansion ceramic calibration plate |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112634373A CN112634373A (en) | 2021-04-09 |
| CN112634373B true CN112634373B (en) | 2023-08-11 |
Family
ID=75307153
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011382690.3A Active CN112634373B (en) | 2020-12-01 | 2020-12-01 | Visual measurement system dynamic correction method based on zero-expansion ceramic calibration plate |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112634373B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114001682B (en) * | 2021-11-19 | 2023-08-01 | 天津博迈科海洋工程有限公司 | Flatness judging method for mounting surface of heavy door frame of electric room module |
| CN115170434A (en) * | 2022-07-28 | 2022-10-11 | 江苏集萃智能光电系统研究所有限公司 | Error correction method and device for line structured light 3D camera |
| CN116935077B (en) * | 2023-07-26 | 2024-03-26 | 湖南视比特机器人有限公司 | Template matching optimization method and system based on encoding and decoding |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101231750A (en) * | 2008-02-21 | 2008-07-30 | 南京航空航天大学 | Calibrating method of binocular three-dimensional measuring system |
| CN102622747A (en) * | 2012-02-16 | 2012-08-01 | 北京航空航天大学 | Camera parameter optimization method for vision measurement |
| CN102663767A (en) * | 2012-05-08 | 2012-09-12 | 北京信息科技大学 | Method for calibrating and optimizing camera parameters of vision measuring system |
| CN104851104A (en) * | 2015-05-29 | 2015-08-19 | 大连理工大学 | Flexible-target-based close-range large-field-of-view calibrate method of high-speed camera |
| CN110345921A (en) * | 2019-06-12 | 2019-10-18 | 中国农业大学 | Stereoscopic fields of view vision measurement and vertical axial aberration and axial aberration bearing calibration and system |
-
2020
- 2020-12-01 CN CN202011382690.3A patent/CN112634373B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101231750A (en) * | 2008-02-21 | 2008-07-30 | 南京航空航天大学 | Calibrating method of binocular three-dimensional measuring system |
| CN102622747A (en) * | 2012-02-16 | 2012-08-01 | 北京航空航天大学 | Camera parameter optimization method for vision measurement |
| CN102663767A (en) * | 2012-05-08 | 2012-09-12 | 北京信息科技大学 | Method for calibrating and optimizing camera parameters of vision measuring system |
| CN104851104A (en) * | 2015-05-29 | 2015-08-19 | 大连理工大学 | Flexible-target-based close-range large-field-of-view calibrate method of high-speed camera |
| CN110345921A (en) * | 2019-06-12 | 2019-10-18 | 中国农业大学 | Stereoscopic fields of view vision measurement and vertical axial aberration and axial aberration bearing calibration and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112634373A (en) | 2021-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112634373B (en) | Visual measurement system dynamic correction method based on zero-expansion ceramic calibration plate | |
| CN109242908B (en) | Calibration method for underwater binocular vision measurement system | |
| CN109859272B (en) | Automatic focusing binocular camera calibration method and device | |
| CN110146038B (en) | Distributed monocular camera laser measuring device and method for assembly corner of cylindrical part | |
| CN109459058B (en) | Calibration method of multi-view-field star sensor based on three-axis turntable | |
| CN105486289B (en) | A kind of laser photography measuring system and camera calibration method | |
| CN111854622B (en) | Large-field-of-view optical dynamic deformation measurement method | |
| CN111047586B (en) | Pixel equivalent measuring method based on machine vision | |
| CN109974618B (en) | Global calibration method of multi-sensor vision measurement system | |
| CN110455198B (en) | Rectangular spline shaft key width and diameter measuring method based on line structure light vision | |
| CN115205466B (en) | Three-dimensional reconstruction method and system for power transmission channel based on structured light | |
| CN110501026B (en) | Camera internal orientation element calibration device and method based on array star points | |
| CN111709985A (en) | Underwater target ranging method based on binocular vision | |
| CN101666625B (en) | Model-free method for correcting distortion error | |
| CN114283203A (en) | Calibration method and system of multi-camera system | |
| CN110108203B (en) | Silk thread position measuring method and system based on photogrammetry technology | |
| CN111289111A (en) | Self-calibration infrared body temperature rapid detection method and detection device | |
| CN115018923A (en) | Method and system for detecting panoramic annular lens parameters | |
| CN115289997A (en) | Binocular camera three-dimensional contour scanner and using method thereof | |
| CN108898585A (en) | A kind of axial workpiece detection method and its device | |
| CN114170321A (en) | Camera self-calibration method and system based on distance measurement | |
| CN112509035A (en) | Double-lens image pixel point matching method for optical lens and thermal imaging lens | |
| CN112649095B (en) | Large-range accurate temperature measurement system based on affine transformation and optical/infrared double lenses | |
| CN112684250B (en) | Calibration method for high-power millimeter wave intensity measurement system | |
| CN113390394B (en) | Light beam method adjustment algorithm with photographic scale |
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 |