CN108038878B - Method and system for determining normal direction and radius of mark point in photogrammetry - Google Patents
Method and system for determining normal direction and radius of mark point in photogrammetry Download PDFInfo
- Publication number
- CN108038878B CN108038878B CN201711084036.2A CN201711084036A CN108038878B CN 108038878 B CN108038878 B CN 108038878B CN 201711084036 A CN201711084036 A CN 201711084036A CN 108038878 B CN108038878 B CN 108038878B
- Authority
- CN
- China
- Prior art keywords
- points
- fitting
- homonymous
- plane
- radius
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 239000013598 vector Substances 0.000 claims abstract description 25
- 238000003384 imaging method Methods 0.000 claims abstract description 23
- 238000001914 filtration Methods 0.000 claims description 13
- 239000011159 matrix material Substances 0.000 claims description 5
- 238000005070 sampling Methods 0.000 claims description 4
- 230000005484 gravity Effects 0.000 claims description 3
- 239000003550 marker Substances 0.000 claims 2
- 230000000694 effects Effects 0.000 abstract description 4
- 238000001514 detection method Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 241001669696 Butis Species 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention relates to a method and a system for determining the normal direction and the radius of a mark point in photogrammetry, wherein the method comprises the following steps: extracting sub-pixel edge points of the mark points imaged in one image, and performing ellipse fitting to obtain imaging points; according to the epipolar geometric relationship and in combination with the imaging points, finding out the homonymous points of the mark points imaged on other multiple images; fitting the plurality of homonymous points by adopting a robust plane fitting method to obtain a fitting plane, solving a normal vector of the mark point through the fitting plane, and obtaining the homonymous points after noise is filtered; and performing circle fitting on the homonymous points after the noise is filtered to obtain the radius of the mark point. The method for determining the normal direction and the radius of the mark point in the photogrammetry can improve the calculation precision of the normal direction and the radius of the mark point, so that the calculation result is closer to the real effect.
Description
Technical Field
The invention relates to the field of calculating a mark point in photogrammetry, in particular to a method and a system for determining the normal direction and the radius of the mark point in photogrammetry.
Background
In the existing method for calculating the mark points in photogrammetry, the calculated normal direction and radius are not accurate, and the information of the mark points attached to the surface of an object cannot be well reflected.
Disclosure of Invention
The invention aims to solve the technical problem of providing a method and a system for determining the normal direction and the radius of a mark point in photogrammetry, which can accurately calculate the normal direction and the radius of the mark point in photogrammetry.
The technical scheme for solving the technical problems is as follows: a method for determining the normal direction and radius of a mark point in photogrammetry comprises the following steps:
s1, extracting sub-pixel edge points of the mark points imaged in one image, and performing ellipse fitting to obtain imaging points;
s2, finding out the homonymous points of the mark points imaged on other images according to the epipolar geometric relationship and by combining the imaging points;
s3, fitting the multiple homonymous points by adopting a robust plane fitting method to obtain a fitting plane, solving a normal vector of the mark point through the fitting plane, and obtaining the homonymous points after noise is filtered;
and S4, performing circle fitting on the homologous points after the noise is filtered to obtain the radius of the mark point.
On the basis of the technical scheme, the invention can be further improved as follows.
Further, in S1, specifically,
s11, binarizing the image formed by the mark points;
s12, extracting edge points of the binarized image;
s13, fitting the ellipse of the extracted edge points to obtain an ellipse;
s14, positioning the ellipse in the image;
s15, dividing the ellipse from the image according to the position of the ellipse, and extracting sub-pixel edge points of the ellipse;
and S16, fitting the ellipse of the sub-pixel edge points to obtain imaging points.
Further, in S3, specifically,
s31, randomly sampling three homonymous points, and performing plane fitting to form a pre-fitting plane;
s32, calculating the distance between all discrete homonymous points and the corresponding pre-fitting plane, and counting the number of the discrete homonymous points with the distance within a preset threshold value;
s33, selecting a pre-fitting plane corresponding to a group of discrete homonymous points with the distance within a preset threshold value and the largest number as a final fitting plane which is successfully fitted;
s34, calculating the spatial positions of three homonymous points needing fitting and forming a fitting plane;
and S35, solving and calculating the normal vector of the fitting plane according to the spatial positions of the three homonymous points needing to be fitted.
Further, in S34, specifically,
s341, respectively calculating internal parameters and pose parameters of the image where the three homonymous points to be fitted are located by adopting a photogrammetry method;
and S342, obtaining the spatial positions of the corresponding homonymous points to be fitted by a front intersection method and combining the internal parameters and the pose parameters of the corresponding images.
Further, the synonym points after the noise is filtered in S3 are the valid synonym points remaining after the discrete synonym points whose distance is not within the preset threshold are removed.
Further, in S4, specifically,
s41, converting the homonymous points after noise filtering to the same plane by using normal vectors;
and S42, performing circle fitting on the noise-filtered homonymous points on the same plane to obtain the radius of the mark point.
Further, in S41, specifically,
s411, respectively carrying out barycenter on the homonymous points after noise filtering to obtain corresponding homonymous barycenter points;
and S412, generating a rotation matrix according to the normal vector, and calculating coordinates of the homonymous point after noise filtering to be converted to the same plane by combining the homonymous point after noise filtering and the corresponding homonymous gravity point.
The invention has the beneficial effects that: the method for determining the normal direction and the radius of the mark point in the photogrammetry can improve the calculation precision of the normal direction and the radius of the mark point, so that the calculation result is closer to the real effect; meanwhile, the calculated coordinates of the mark points can be better matched with a handheld scanner for use when scanning large parts, and the thickness of the mark plate can be compensated after the mark points are registered to the model, so that the mark points can be registered more accurately, and the quality of the object can be determined more accurately.
Based on the method for determining the normal direction and the radius of the mark point in the photogrammetry, the invention also provides a system for determining the normal direction and the radius of the mark point in the photogrammetry.
A system for determining the normal direction and radius of a mark point in photogrammetry comprises an imaging point generating module, a homonymy point generating module, a normal direction calculating module and a radius calculating module,
the imaging point generating module is used for extracting sub-pixel edge points of the mark points imaged in one image and performing ellipse fitting to obtain imaging points;
the homonymy point generating module is used for finding out homonymy points of the mark points imaged on other multiple images according to the epipolar geometric relationship and by combining the imaging points;
the normal calculation module is used for fitting the plurality of homonymous points by adopting a robust plane fitting method to obtain a fitting plane, solving a normal vector of the mark point through the fitting plane, and obtaining the homonymous points after noise is filtered;
and the radius calculation module is used for performing circle fitting on the homonymous points after the noise is filtered out to obtain the radius of the mark point.
The invention has the beneficial effects that: the system for determining the normal direction and the radius of the mark point in the photogrammetry can improve the calculation precision of the normal direction and the radius of the mark point, so that the calculation result is closer to the real effect; meanwhile, the calculated coordinates of the mark points can be better matched with a handheld scanner for use when scanning large parts, and the thickness of the mark plate can be compensated after the mark points are registered to the model, so that the mark points can be registered more accurately, and the quality of the object can be determined more accurately.
Drawings
FIG. 1 is a flow chart of a method of determining normal and radius of a landmark point in a photogrammetry according to the present invention;
FIG. 2 is a block diagram of a system for determining normal and radius of a landmark point in a photogrammetry according to the present invention.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, which are set forth by way of illustration only and are not intended to limit the scope of the invention.
As shown in fig. 1, a method for determining the normal direction and radius of a mark point in photogrammetry comprises the following steps:
and S1, extracting sub-pixel edge points of the mark points imaged in one image, and performing ellipse fitting to obtain imaged points.
Specifically, the step S1 is,
s11, binarizing the image formed by the mark points; (the camera takes a picture of the landmark points, which are approximately an ellipse in the image, and the camera takes pictures at different positions, which can all show an ellipse).
And S12, extracting edge points of the binarized image.
And S13, fitting the ellipse to the extracted edge points to obtain the ellipse.
S14, the position of the ellipse is located in the image.
S15, dividing the ellipse from the image according to the position of the ellipse, and extracting sub-pixel edge points of the ellipse; wherein, the sub-pixel edge points represent: assuming that the real object is imaged on the camera, we can generally say that he is on the 6 th pixel, but now the position can be accurate to 5.2 images, called sub-pixels, which is less than one pixel accurate.
S16, fitting an ellipse to the sub-pixel edge points to obtain imaging points (including parameters of the imaging points); the following is a specific calculation procedure for the fitting of the ellipse:
ax2+bxy+cy2+dx+ey+f＝0 (1)
a, b, c, d, e and f all represent the coefficients of an elliptic equation and represent the parameters to be solved; x, y represent coordinate points on the ellipse; equation (1) represents an elliptic equation. The representation of the ellipse has two forms, one is formula (1); the other is represented by the center, the long half shaft and the short half shaft of the ellipse and the angle; the two representations may be converted to each other.
In equation (2), (x1, y 1. (xn, yn) represents discrete points on the ellipse circumference, with the aim of using these discrete points to fit the a, b, c, d, e, f parameters of the ellipse.
The expression form of the conversion formula (2) is AU ═ 0 (3)
UDV, as obtained by equation (3)T＝SVD(ATA) (4)
Taking the last column vector of V as the value of U, then
The x coordinate of the center of the ellipse is
The y coordinate of the center of the ellipse is
The ellipse major semi-axis is
The ellipse minor semi-axis is
The deflection angle of the ellipse is
S2, intersecting the epipolar lines with the imaging points in the multiple images respectively according to the epipolar line corresponding relation among the multiple images to obtain the homonymy points of the mark points imaged on the multiple images; the same-name point is the image of the same mark point on different images, namely a mark point is placed on the ground, the mark point is the image of different images, and the images of all the same mark points are the same-name points; the core correspondence specifically means that after the relative positions of the images are determined, a point of the same name point on one of the images is mapped to a line on the other image.
And S3, fitting the multiple homonymous points by adopting a robust plane fitting method to obtain a fitting plane, solving the normal vector of the mark point through the fitting plane, and obtaining the homonymous points after noise is filtered.
Specifically, the step S3 is,
and S31, randomly sampling three homonymous points, and performing plane fitting to form a pre-fitting plane.
S32, calculating the distance between all discrete homonymous points and the corresponding pre-fitting plane, and counting the number of the discrete homonymous points with the distance within a preset threshold value; the homonymous points with the distance smaller than the set threshold value are also called interior points; the calculation of the pre-fit plane is as follows:
suppose there are three homologous points P at random0(x0，y0，z0)、P1(x1，y1，z1) And P2(x2，y2，z2) Wherein
(
Is defined as P0、P1And P2Average points obtained by averaging the three points); the normal L to this pre-fit plane is equal to (P)1-P0)*(P2-P0) (ii) a The equation of the pre-fitted plane is
(
Meaning that the representative point is on a plane); distance of discrete homologous points to corresponding pre-fitted planes
(
Indicating that the discrete points are approximately on a plane with some error from the plane, this error is minimized to find the normal direction. That is to say using P0，P1，P2Fitting three points on a fitting plane, butIs the point from P4 to Pn is near the plane of fit, so there is some error, denoted by d), where Pt represents the discrete homologous point.
S33, selecting a pre-fitting plane corresponding to a group of discrete homonymous points with the distance within a preset threshold value and the largest number as a final fitting plane which is successfully fitted; for example: if the ratio of the statistical points to the total points reaches a set ratio, the plane fitting is considered to be successful; for example, if three points of 9 approximate points are adopted, the plane fitted is good, the other 6 points close to the plane can be found out, and the 6 points are considered as interior points, and the ratio of the final statistic points to the total points is 9/10-90%; if the point that is far away is sampled, the plane fit is poor and the remaining 7 approximation points are too far from the plane of error.
And S34, calculating the spatial positions of three homonymous points needing to be fitted and forming a fitting plane.
Specifically, the step S34 is,
and S341, respectively calculating internal parameters and pose parameters of the image where the three homonymous points needing to be fitted are located by adopting a photogrammetry method.
And S342, obtaining the spatial positions of the corresponding homonymous points to be fitted by a front intersection method and combining the internal parameters and the pose parameters of the corresponding images.
And S35, solving and calculating the normal vector of the fitting plane according to the spatial positions of the three homonymous points needing to be fitted.
The homonymous points after the noise is filtered in S3 are the remaining effective homonymous points after the discrete homonymous points whose distance is not within the preset threshold are removed.
And S4, performing circle fitting on the homologous points after the noise is filtered to obtain the radius of the mark point.
Specifically, the step S4 is,
and S41, converting the homologous points after the noise is filtered to the same plane by using the normal vector.
Specifically, the step S41 is,
s411, respectively carrying out barycenter on the homonymous points after noise filtering to obtain corresponding homonymous barycenter points; for example, the noise-filtered homonymous point X is subjected to barycenter transformation to obtain a corresponding homonymous barycenter point X0。
S412, generating a rotation matrix according to the normal vector, and calculating coordinates of the homonymous points after noise filtering to be converted to the same plane by combining the homonymous points after noise filtering and the corresponding homonymous gravity points; the specific calculation process is as follows:
generating a rotation matrix R according to the normal vector, and searching a value with the maximum total absolute value of n1, n2 and n3 under the condition that the column vector n is (n1, n2 and n3) to represent the normal vector;
a. assuming that n1 is the largest, i.e., the normal is closer to the x direction, let n ═ (-n2, n1,0) and convert it to a vector with a modulo length of 1;
b. assuming that n2 is the largest, i.e., the normal is closer to the y direction, let n ═ (-n2, n1,0) and convert it to a vector with a modulo length of 1;
c assuming n3 is the largest, i.e. normal closer to the z direction, let n' be (0, -n3, n2) and convert it to a vector with a modulo length of 1;
n ″, n cross-multiplied by n';
the rotation matrix is R ═ n ', n ″, where n, n', n ″ are in a column arrangement, and finally converted point coordinates XT ═ R (X-X0) are obtained.
S42, performing circle fitting on the noise-filtered homonymous points on the same plane to obtain the radius of the mark point; the following is a specific calculation procedure for circle fitting:
x2+y2+ax+by+c＝0 (5)
a, b and c represent coefficients of a circular equation and represent parameters to be solved; x, y represent coordinate points on the circle; equation (5) represents a circular equation. The expression of the circle has two forms, one is formula (1), and the other is the center and radius of the circle, and the two expression modes can be converted with each other.
(x1, y 1.) the term (xn, yn) denotes the point on the circumference, which is the filtered point.
The expression form of conversion formula (6) is AU ═ B (7)
Wherein,
U＝[a b c]T，
u ═ a can be obtained according to formula (7)TA)-1*ATB (8)
The center x coordinate of the circle is x0 ═ a/2,
the center y coordinate of the circle is-b/2 as y0,
the radius of the circle is
The photogrammetry can be widely used for the high-precision measurement of key points of industrial parts, the quality detection and reverse design of industrial parts, the measurement of large parts by matching with a handheld scanner and the like, for example, in the later quality detection, the position of a point on the surface of a part needs to be reflected, the thickness of a mark point needs to be subtracted, the thickness direction is also related to the normal direction, so the precision of the normal direction and the radius of the used mark point influences the later quality detection, and the normal direction and the radius of the mark point determined by the method can reduce the error of the later quality detection.
Based on the method for determining the normal direction and the radius of the mark point in the photogrammetry, the invention also provides a system for determining the normal direction and the radius of the mark point in the photogrammetry.
As shown in FIG. 2, a system for determining the normal direction and radius of a mark point in photogrammetry comprises an imaging point generating module, a homonymy point generating module, a normal direction calculating module and a radius calculating module,
the imaging point generating module is used for extracting sub-pixel edge points of the mark points imaged in one image and performing ellipse fitting to obtain imaging points;
the homonymy point generating module is used for finding out homonymy points of the mark points imaged on other multiple images according to the epipolar geometric relationship and by combining the imaging points;
the normal calculation module is used for fitting the plurality of homonymous points by adopting a robust plane fitting method to obtain a fitting plane, solving a normal vector of the mark point through the fitting plane, and obtaining the homonymous points after noise is filtered;
and the radius calculation module is used for performing circle fitting on the homonymous points after the noise is filtered out to obtain the radius of the mark point.
The system for determining the normal direction and the radius of the mark point in the photogrammetry can improve the calculation precision of the normal direction and the radius of the mark point, so that the calculation result is closer to the real effect; meanwhile, the calculated coordinates of the mark points can be better matched with a handheld scanner for use when scanning large parts, and the thickness of the mark plate can be compensated after the mark points are registered to the model, so that the mark points can be registered more accurately, and the quality of the object can be determined more accurately.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (7)
1. A method for determining the normal direction and radius of a mark point in photogrammetry is characterized in that: the method comprises the following steps:
s1, extracting sub-pixel edge points of the mark points imaged in one image, and performing ellipse fitting to obtain imaging points;
s2, finding out the homonymous points of the mark points imaged on other images according to the epipolar geometric relationship and by combining the imaging points;
s3, fitting the multiple homonymous points by adopting a robust plane fitting method to obtain a fitting plane, solving a normal vector of the mark point through the fitting plane, and obtaining the homonymous points after noise is filtered;
s4, performing circle fitting on the homonymous points after noise filtering to obtain the radius of the mark point;
wherein, in the step S3, a robust plane fitting method is adopted to fit a plurality of homonymous points to obtain a fitting plane, and a normal vector of the mark point is solved through the fitting plane, specifically,
s31, randomly sampling three homonymous points, and performing plane fitting to form a pre-fitting plane;
s32, calculating the distance between all discrete homonymous points and the corresponding pre-fitting plane, and counting the number of the discrete homonymous points with the distance within a preset threshold value;
s33, selecting a pre-fitting plane corresponding to a group of discrete homonymous points with the distance within a preset threshold value and the largest number as a final fitting plane which is successfully fitted;
s34, calculating the spatial positions of three homonymous points needing fitting and forming a fitting plane;
and S35, solving and calculating the normal vector of the fitting plane according to the spatial positions of the three homonymous points needing to be fitted.
2. The method of claim 1, wherein the method further comprises the steps of: specifically, the step S1 is,
s11, binarizing the image formed by the mark points;
s12, extracting edge points of the binarized image;
s13, fitting the ellipse of the extracted edge points to obtain an ellipse;
s14, positioning the ellipse in the image;
s15, dividing the ellipse from the image according to the position of the ellipse, and extracting sub-pixel edge points of the ellipse;
and S16, fitting the ellipse of the sub-pixel edge points to obtain imaging points.
3. A method for determining the normal and radius of a marker point in a photogrammetry as claimed in claim 1 or 2, wherein: specifically, the step S34 is,
s341, respectively calculating internal parameters and pose parameters of the image where the three homonymous points to be fitted are located by adopting a photogrammetry method;
and S342, obtaining the spatial positions of the corresponding homonymous points to be fitted by a front intersection method and combining the internal parameters and the pose parameters of the corresponding images.
4. A method for determining the normal and radius of a marker point in a photogrammetry as claimed in claim 1 or 2, wherein: the homonymous points after the noise is filtered in S3 are the remaining effective homonymous points after the discrete homonymous points whose distance is not within the preset threshold are removed.
5. The method of claim 4, wherein the normal direction and the radius of the mark point in the photogrammetry are determined by: specifically, the step S4 is,
s41, converting the homonymous points after noise filtering to the same plane by using normal vectors;
and S42, performing circle fitting on the noise-filtered homonymous points on the same plane to obtain the radius of the mark point.
6. The method of claim 5, wherein the method further comprises the steps of: specifically, the step S41 is,
s411, respectively carrying out barycenter on the homonymous points after noise filtering to obtain corresponding homonymous barycenter points;
and S412, generating a rotation matrix according to the normal vector, and calculating coordinates of the homonymous point after noise filtering to be converted to the same plane by combining the homonymous point after noise filtering and the corresponding homonymous gravity point.
7. A system for determining the normal and radius of a landmark point in a photogrammetry, comprising: comprises an imaging point generating module, a homonymy point generating module, a normal calculating module and a radius calculating module,
the imaging point generating module is used for extracting sub-pixel edge points of the mark points imaged in one image and performing ellipse fitting to obtain imaging points;
the homonymy point generating module is used for finding out homonymy points of the mark points imaged on other multiple images according to the epipolar geometric relationship and by combining the imaging points;
the normal calculation module is used for fitting the plurality of homonymous points by adopting a robust plane fitting method to obtain a fitting plane, solving a normal vector of the mark point through the fitting plane, and obtaining the homonymous points after noise is filtered;
the radius calculation module is used for performing circle fitting on the homonymous points after noise filtering to obtain the radius of the mark point;
wherein the normal calculation module is specifically configured to,
randomly sampling three homonymous points, and performing plane fitting to form a pre-fitting plane;
calculating the distances from all the discrete homonymous points to the corresponding pre-fitting planes, and counting the number of the discrete homonymous points with the distances within a preset threshold value;
selecting a pre-fitting plane corresponding to a group of discrete homonymous points with the distance within a preset threshold and the largest number as a fitting plane which is finally successfully fitted;
calculating the spatial positions of three homonymous points needing fitting and forming a fitting plane;
and solving to calculate a normal vector of the fitting plane through the spatial positions of the three homonymous points needing fitting.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711084036.2A CN108038878B (en) | 2017-11-07 | 2017-11-07 | Method and system for determining normal direction and radius of mark point in photogrammetry |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711084036.2A CN108038878B (en) | 2017-11-07 | 2017-11-07 | Method and system for determining normal direction and radius of mark point in photogrammetry |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108038878A CN108038878A (en) | 2018-05-15 |
| CN108038878B true CN108038878B (en) | 2021-02-12 |
Family
ID=62093883
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711084036.2A Active CN108038878B (en) | 2017-11-07 | 2017-11-07 | Method and system for determining normal direction and radius of mark point in photogrammetry |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108038878B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5771309A (en) * | 1993-03-26 | 1998-06-23 | Honda Giken Kogyo Kabushiki Kaisha | Method for measuring position of hole |
| CN1566900A (en) * | 2003-06-11 | 2005-01-19 | 北京航空航天大学 | Vision measuring method for spaced round geometrical parameters |
| CN101261115A (en) * | 2008-04-24 | 2008-09-10 | 吉林大学 | Spatial circular geometric parameter binocular stereo vision measurement method |
-
2017
- 2017-11-07 CN CN201711084036.2A patent/CN108038878B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5771309A (en) * | 1993-03-26 | 1998-06-23 | Honda Giken Kogyo Kabushiki Kaisha | Method for measuring position of hole |
| CN1566900A (en) * | 2003-06-11 | 2005-01-19 | 北京航空航天大学 | Vision measuring method for spaced round geometrical parameters |
| CN101261115A (en) * | 2008-04-24 | 2008-09-10 | 吉林大学 | Spatial circular geometric parameter binocular stereo vision measurement method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108038878A (en) | 2018-05-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109146980B (en) | Monocular vision based optimized depth extraction and passive distance measurement method | |
| WO2021115071A1 (en) | Three-dimensional reconstruction method and apparatus for monocular endoscope image, and terminal device | |
| CN109035320B (en) | Monocular vision-based depth extraction method | |
| CN106651752B (en) | Three-dimensional point cloud data registration method and splicing method | |
| CN104484648B (en) | Robot variable visual angle obstacle detection method based on outline identification | |
| CN109544628B (en) | Accurate reading identification system and method for pointer instrument | |
| CN107084680B (en) | Target depth measuring method based on machine monocular vision | |
| CN107729893B (en) | Visual positioning method and system of die spotting machine and storage medium | |
| CN110378969B (en) | Convergent binocular camera calibration method based on 3D geometric constraint | |
| CN102075785B (en) | Method for correcting wide-angle camera lens distortion of automatic teller machine (ATM) | |
| CN102075736B (en) | Camera calibration method for high-definition intelligent internet protocol (IP) camera | |
| DE112011102132T5 (en) | Method and device for image-based positioning | |
| CN110672020A (en) | Stand tree height measuring method based on monocular vision | |
| CN109242779B (en) | Method and device for constructing camera imaging model and automobile automatic driving system | |
| CN111524174B (en) | Binocular vision three-dimensional construction method for moving platform moving target | |
| CN113012234B (en) | High-precision camera calibration method based on plane transformation | |
| CN112270719B (en) | Camera calibration method, device and system | |
| CN110223355B (en) | Feature mark point matching method based on dual epipolar constraint | |
| CN107633532B (en) | Point cloud fusion method and system based on white light scanner | |
| CN107592922A (en) | Method for implementing operation to ground | |
| CN111340888B (en) | Light field camera calibration method and system without white image | |
| CN111383194A (en) | Camera distortion image correction method based on polar coordinates | |
| WO2012133371A1 (en) | Image capture position and image capture direction estimation device, image capture device, image capture position and image capture direction estimation method and program | |
| CN115222819A (en) | Camera self-calibration and target tracking method based on multi-mode information reference in airport large-range scene | |
| CN112801141B (en) | Heterogeneous image matching method based on template matching and twin neural network optimization |
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 |