CN108447092A - The method and device of vision positioning marker - Google Patents
The method and device of vision positioning marker Download PDFInfo
- Publication number
- CN108447092A CN108447092A CN201810118800.1A CN201810118800A CN108447092A CN 108447092 A CN108447092 A CN 108447092A CN 201810118800 A CN201810118800 A CN 201810118800A CN 108447092 A CN108447092 A CN 108447092A
- Authority
- CN
- China
- Prior art keywords
- camera
- current frame
- frame image
- marker
- point
- 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 61
- 239000003550 marker Substances 0.000 title claims abstract description 60
- 239000000284 extract Substances 0.000 claims abstract description 5
- 239000011159 matrix material Substances 0.000 claims description 18
- 238000003708 edge detection Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 6
- 238000013519 translation Methods 0.000 claims description 6
- 238000003384 imaging method Methods 0.000 claims description 4
- 238000000205 computational method Methods 0.000 claims description 2
- 238000010276 construction Methods 0.000 claims description 2
- 230000006870 function Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 241000208340 Araliaceae Species 0.000 description 2
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 235000008434 ginseng Nutrition 0.000 description 2
- 238000010191 image analysis Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000003190 augmentative effect Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention belongs to computer vision fields, and in particular to a kind of method and device of vision positioning marker.Aim to solve the problem that the prior art causes camera to carry out the inaccurate problem of positioning by existing mark.The present invention provides a kind of method of vision positioning marker, including obtains the current frame image of input video, extracts the edge graph picture point of current frame image;Clustering is carried out to edge picture point, conic fitting is carried out according to different classes;Based on conic section calculating current frame image to polar curve, and obtain conic section and the intersection point to polar curve;According to the camera intrinsic parameter and intersection point of the current frame image obtained in advance, the camera pose parameter for calculating current frame image is realized to marker positioning.The method of the present invention has the advantages that easy, speed is fast, occupy small memory and precision and robustness are high.
Description
Technical field
The invention belongs to computer vision fields, and in particular to a kind of method and device of vision positioning marker.
Background technology
With the fast development of virtual reality, augmented reality and robotics, the tracking and calculating conduct of camera position
A wherein indispensable technology obtains a large amount of concerns and research of academia and industrial quarters.The prior art is to camera position meter
Calculating one of most efficient method is carried out based on plane mark object, on the basis of concentric circles marker is suggested, is added
Then there is annular marker in succession in color and dimensional information, marker contains simple graph and the matrix of texture, rectangular
Mark, four circles are located at a variety of markers such as the mark at four angles of a rectangle, black rectangle containing black and white block,
But the marker of prior art design needs multiple spatial points and picture point to be matched, and then carries out phase according to perspective N point methods
Set calculating in seat in the plane.But if there is a spatial point and picture point matching error, camera position and Attitude Calculation will be caused not
Accurately, even if rejecting the point of matching error using RANSAC (Random Sample Consensus) algorithm, but due to existing
Point in the marker of technology is less, it is impossible to ensure that the point rejected is the point of matching error, while also adding answering for algorithm
Miscellaneous degree and the wasting of resources.
Therefore, how to propose a kind of solution to cause camera to carry out the inaccurate scheme of positioning by existing mark to be this field skill
The current problem to be solved of art personnel.
Invention content
In order to solve the above problem in the prior art, in order to solve the prior art by it is existing mark cause camera into
The inaccurate problem of row positioning, the present invention provides a kind of methods of vision positioning marker, including:
The current frame image for obtaining input video, extracts the edge graph picture point of the current frame image;
Clustering is carried out to the edge image point, conic fitting is carried out according to different classes;
Based on the conic section calculate the current frame image to polar curve, and obtain the conic section and described right
The intersection point of polar curve;
According to the camera intrinsic parameter of the current frame image obtained in advance and the intersection point to polar curve, work as described in calculating
The camera pose parameter of prior image frame, which is realized, positions marker.
In the optimal technical scheme of the above method, the method further includes:
Construction include the circular indicia object of circular contour and mark point, the mark point be located at circular contour inside or
Outside the circular contour, the circular contour is used for conic fitting.
In the optimal technical scheme of the above method, the camera pose parameter of the current frame image includes the rotation of camera
The translation vector of matrix and camera.
In the optimal technical scheme of the above method, the camera pose parameter of the current frame image is calculated, method is:
According to the imaging process of camera, the conic section is established and described to the intersection point of polar curve and the camera pose
The mathematical relationship of the camera spin matrix of parameter, shown in the specific following formula of mathematical relationship:
According to the spatial relation of the marker and the camera, the camera pose ginseng of the current frame image is calculated
Number, shown in the specific following formula of computational methods:
Wherein, t indicates the translation vector of camera, s0、s1Indicate intermediate variable, r1Indicate the first of camera spin matrix
Row, m0Indicate the origin image of world coordinate system, m1Indicate the label point image of marker, l∞Indicate described to polar curve, LxIt indicates
Coordinate of the mark point of marker in space coordinates, r11、r21、r31Corresponding element in camera spin matrix is indicated respectively,
(u0, v0) indicate m0Coordinate, (u1, v1) indicate m1Coordinate;
The spatial relation of the marker and shown camera is:The marker is located in front of the camera, is described
The normal direction of plane is directed toward the camera where marker.
In the optimal technical scheme of the above method, " the edge graph picture point for extracting the current frame image ", method is:
The edge graph picture point of the current frame image is extracted using edge detection algorithm.
In the optimal technical scheme of the above method, " based on the conic section calculate the current frame image to pole
Line ", method are:
When the quantity of the conic section is two, calculated according to quasi- affine-invariant features described to polar curve;
When the quantity of the conic section is one, the point inside the conic section is extracted as world coordinate system
Origin, calculate the origin of the world coordinate system to polar curve, as the conic section to polar curve.
The present invention also provides a kind of storage devices, wherein being stored with a plurality of program, described program is suitable for being loaded by processor
And the method for executing vision positioning marker as described above.
The present invention also provides a kind of processing units, including processor, storage device;Processor is adapted for carrying out each program;
Storage device is suitable for storing a plurality of program;Described program is suitable for being loaded by processor and executing vision positioning as described above
The method of marker.
Compared with the immediate prior art, it includes obtaining to input that the present invention, which provides a kind of method of vision positioning marker,
The current frame image of video extracts the edge graph picture point of current frame image;The current frame image of input video is obtained, extraction is current
The edge graph picture point of frame image;Based on conic section calculate current frame image to polar curve, and obtain conic section and to polar curve
Intersection point;According to the camera intrinsic parameter and intersection point of the current frame image obtained in advance, the camera pose ginseng of current frame image is calculated
Number, which is realized, positions marker.
Above-mentioned technical proposal at least has the advantages that:Technical scheme of the present invention can be selected without multiple spot
On the basis of matched, the position of camera and posture are parsed completely, have that easy, speed is fast, the small and precision that occupies memory
The high feature with robustness.In addition, the marker of the present invention program is simply easy to make, and include often this in daily natural scene
Category information, the result positioned to marker can be under natural scene as the testing standard positioned based on natural scene
The case where camera positioning no true value, provides reference data, and it is fixed can to carry out camera in real time online on the cpu resource of low configuration
Position.
Description of the drawings
Fig. 1 is the flow diagram of the vision positioning marker method of an embodiment of the present invention;
Fig. 2 is the schematic diagram of the first kind marker of an embodiment of the present invention;
Fig. 3 is the schematic diagram of the second class marker of an embodiment of the present invention.
Specific implementation mode
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
The every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention
The preferred embodiment of the present invention described with reference to the accompanying drawings.It will be apparent to a skilled person that this
A little embodiments are used only for explaining the technical principle of the present invention, it is not intended that limit the scope of the invention.
Refering to attached drawing 1, Fig. 1 illustratively gives the flow signal of the method for vision positioning marker in the present embodiment
Figure.As shown in Figure 1, the method for vision positioning marker includes the following steps in the present embodiment:
Step S1:The current frame image for obtaining input video, extracts the edge graph picture point of the current frame image;
The method of the vision positioning marker of the present invention may be implemented to be identified the current frame image of the video of input
Object positions, and important link of the edge detection as image analysis and identification, can largely influence the accuracy of identification,
Therefore it needs to extract the edge graph picture point of current frame image, to carry out subsequent operation.
In one preferred embodiment of the invention, the edge image of current frame image is extracted using edge detection algorithm
Point.
Edge detection plays an important role in the applications such as computer vision, image analysis, other features of image are all
It is derived by edge and these essential characteristics of region, the effect of edge detection will have a direct impact on segmentation and the identity of image
Energy.Edge detection is actually that the difference using object and background on characteristics of image detects to realize, specifically, edge detection
Four filtering, enhancing, detection and positioning steps, the edge graph picture point extracted can be divided into.
Step S2:Clustering is carried out to the edge image point, conic fitting is carried out according to different classes;
After obtaining edge graph picture point, clustering is carried out to edge picture point, wherein clustering refers to a kind of searching number
All data instances are organized into some similar groups by the technology of immanent structure between, cluster, and similar group can become cluster, gather
Alanysis is also a kind of unsupervised learning.After obtaining edge graph picture point, according to the attribute of edge graph picture point, it is classified as different
Classification carries out conic fitting further according to different classes.
Step S3:Based on the conic section calculate the current frame image to polar curve, and obtain the conic section
With the intersection point to polar curve;
In practical applications, after being fitted to conic section according to different classes, the secondary song of different number can be obtained
The method to polar curve of line, the conic section calculating current frame image of different number is also different, specifically, the quantity of conic section
Can be two or one, after obtaining conic section, calculate conic section and intersection point to polar curve, and by conic section with
It is corresponding with mark point in marker to the value of polar curve intersection point, by the way that the current frame image foundation of marker and video is contacted,
The number of matches of mark point can be reduced in post-processing, processing speed is faster.
Step S4:According to the camera intrinsic parameter of the current frame image obtained in advance and the intersection point, work as described in calculating
The camera pose parameter of prior image frame, which is realized, positions marker.
In embodiments of the present invention, camera intrinsic parameter can be previously known, can also pass through in unknown camera intrinsic parameter
After solving camera intrinsic parameter, according to camera intrinsic parameter, conic section with to the intersection point of polar curve, the phase seat in the plane of current frame image is calculated
Appearance parameter calculates camera according to the imaging process of camera, the spatial position of camera and marker in conjunction with the mark point of marker
Pose parameter, the positioning to marker is completed with this.
The method of the present invention is based on a kind of circular plane mark object, without carrying out multiple spot matching, the position of camera and appearance
State can parse completely, not only facilitate, processing speed is fast but also committed memory is small, precision and robustness height.
It in the preferred embodiment of the present invention, can be by the current frame image of acquisition video, according to each width
The information of image calculates the intrinsic parameter of camera, is converted to image according to the intrinsic parameter of camera, the figure after being converted
Picture solves the pose parameter of camera according to the image after transformation.
Specifically, a given secondary tag image, is imaged as conic section by perspective camera by the circle in tag image, carries
The point in specific conic section edge image in image is taken, specific conic section is denoted as M, the point extracted is denoted as mi, meter
The point m extractediTo the geometric distance d of conic section Mfa(mi, C), wherein C is the coefficient matrix of conic section M, to several
What distance carries out linear weighted function iteration, is obtained and the relevant Matrix Cs of C with singular value decomposition method1, using based on most short geometry
Distance d (mi, C) structure object function, calculating work as C=C1When small quantity Δ u when making the minimization of object functioni、ΔviWith
And scale parameter λiValue, with small quantity Δ ui、ΔviAnd scale parameter λiInitial value, to object function carry out it is non-linear
Optimization Solution obtains coefficient matrix C2, according to coefficient matrix C2Generate the conic section after specific conic section M optimizations in image
M2。
Further, as shown in Fig. 2, Fig. 2 illustratively gives the schematic diagram of first kind marker, by (a) figure in Fig. 2
Origin of the center of circle of the circle with stain as world coordinate system as in, using the line in two round centers of circle as world coordinate system
X-axis;Using the center of circle of (b) image concentric circles in Fig. 2 as the origin of world coordinates axis, the line of origin and the stain in annulus is made
For the X-axis of world coordinate system, the origin image of world coordinate system is denoted as m0, by the image in second center of circle or the figure of stain
As being denoted as m1, the coordinate of the spatial point is denoted as (Lx,0,0,1).Fig. 3 illustratively gives the schematic diagram of the second class marker, by
One circle, the center of circle, the outer stain composition of circle, the center of circle are used as world coordinate system origin, and the center of circle is connected to world's seat with the outer stain of circle
Mark system X-axis, (a) is specific form, (b) in be (a) two examples.
Based on Fig. 2, using quasi- affine-invariant features, calculate separately (a) in Fig. 2, in (b) two images particular point image,
The real and imaginary parts of the image of particular point are denoted as m respectivelyr1, mr2, using the line of particular point as plane where tag image
Line at infinity picture, is denoted as l∞, antipodal points of the line at infinity picture about conic section is calculated, i.e., the circle of space circle in image
Heart picture point.It is to be denoted as m respectively by two of (a) image in Fig. 2 round center of circle picture points0、m1, by Fig. 2 (b) image it is same
The center of circle of heart circle is denoted as m0, the image of stain is denoted as m1。
Based on Fig. 3, the image in the center of circle is directly extracted as m0.Calculate m0About conic section to polar curve, as l∞。
m1For the image of stain.Calculate l∞With the intersection point of conic section, result is a pair of of complex conjugate point, and real imaginary part as before, be denoted as respectively
mr1And mr2。
Known to camera intrinsic parameter, spatial point is remembered under world coordinate system to the transformation under camera coordinates system
For R (r1, r2, r3), t, wherein R indicate 3*3 spin matrix, r1, r2, r3For 3 row of spin matrix, t indicates that length is 3
Vector represents the translation of camera, according to the imaging process of camera, can obtain formula (1):
According to the spatial relation of marker and camera, the camera pose parameter of current frame image is calculated, it is specific to count
Shown in calculation method such as formula (2):
Wherein, t indicates the translation vector of camera, s0、s1Indicate intermediate variable, r1Indicate the first of camera spin matrix
Row, m0Indicate the origin image of world coordinate system, m1Indicate the label point image of marker, l∞Indicate described to polar curve, LxIt indicates
Coordinate of the mark point of marker in space coordinates, r11、r21、r31Corresponding element in camera spin matrix is indicated respectively,
(u0, v0) indicate m0Coordinate, (u1, v1) indicate m1Coordinate;
The spatial relation of marker and camera is:The normal direction of plane where marker is located at camera front, marker
It is directed toward camera, t can be uniquely determined according to formula (1), according to the spatial relation and r of camera and marker33<0, it can be with
Uniquely determine s3Symbol, therefore r3It can also uniquely determine, then r2=r3×r1It can also uniquely determine, therefore, camera
Pose parameter R=(r1,r2r3), t, which is solved, to be come.
In the case where camera intrinsic parameter is unknown, the intrinsic parameter of camera is solved first, image is become according to intrinsic parameter
It changes, the pose parameter of camera is solved according still further to above method.
Specifically, camera intrinsic parameter method for solving is as follows:
Shown in the Intrinsic Matrix such as formula (3) for setting camera:
Wherein, f1And f2It is the parameter that can change, according to above formula and mr1、mr2, intrinsic parameter K can be calculated, specifically
Shown in method such as formula (4) and formula (5):
Wherein,
Formula (4) and formula (5) are about g1、g2Linear equation, it is assumed that mr1And mr2Coordinate be respectively mr1=(a1,
a2,a3)、mr1=(a1,a2,a3), by mr1And mr2Value substitute into formula (4) and formula (5), can solve to obtain f1And f2Value:
According to the information of every piece image, the intrinsic parameter of camera can be calculated, the intrinsic parameter of camera can be with image
The variation of frame number and change, therefore the present invention method also be adapted for zoom camera.
The step of method described in conjunction with the examples disclosed in this document or algorithm, can use hardware, processor to execute
The combination of software module or the two is implemented.Software module can be placed in random access memory (RAM), memory, read-only memory
(ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technical field
In any other form of storage medium well known to interior.
The present invention also provides a kind of storage devices, wherein being stored with a plurality of program, described program is suitable for being loaded by processor
And the method for executing such as above-mentioned vision positioning marker.
Person of ordinary skill in the field can be understood that for convenience of description and succinctly, the present invention is real
The specific work process and related description of the storage device of example are applied, the method that can refer to foregoing visual location marker is implemented
Example in corresponding process, and with the method advantageous effect having the same of above-mentioned vision positioning marker, details are not described herein.
A kind of processing unit, including processor, storage device;Processor is adapted for carrying out each program;Storage device is fitted
In a plurality of program of storage;Described program is suitable for being loaded by processor and being executed the method such as above-mentioned vision positioning marker.
Person of ordinary skill in the field can be understood that for convenience of description and succinctly, the present invention is real
The specific work process and related description of the processing unit of example are applied, the method that can refer to foregoing visual location marker is implemented
Example in corresponding process, and with the method advantageous effect having the same of above-mentioned vision positioning marker, details are not described herein.
Those skilled in the art should be able to recognize that, side described in conjunction with the examples disclosed in the embodiments of the present disclosure
Method step, can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate electronic hardware and
The interchangeability of software generally describes each exemplary composition and step according to function in the above description.These
Function is executed with electronic hardware or software mode actually, depends on the specific application and design constraint of technical solution.
Those skilled in the art can use different methods to achieve the described function each specific application, but this reality
Now it should not be considered as beyond the scope of the present invention.
So far, it has been combined preferred embodiment shown in the drawings and describes technical scheme of the present invention, still, this field
Technical staff is it is easily understood that protection scope of the present invention is expressly not limited to these specific implementation modes.Without departing from this
Under the premise of the principle of invention, those skilled in the art can make the relevant technologies feature equivalent change or replacement, these
Technical solution after change or replacement is fallen within protection scope of the present invention.
Claims (8)
1. a kind of method of vision positioning marker, which is characterized in that including:
The current frame image for obtaining input video, extracts the edge graph picture point of the current frame image;
Clustering is carried out to the edge image point, conic fitting is carried out according to different classes;
Based on the conic section calculate the current frame image to polar curve, and obtain the conic section and described to polar curve
Intersection point;
According to the camera intrinsic parameter of the current frame image obtained in advance and the intersection point to polar curve, the present frame is calculated
The camera pose parameter of image, which is realized, positions marker.
2. according to the method described in claim 1, it is characterized in that, the method further includes:
Construction includes the circular indicia object of circular contour and mark point, and the mark point is located inside the circular contour or described
Outside circular contour, the circular indicia object is used for conic fitting.
3. according to the method described in claim 1, it is characterized in that, the camera pose parameter of the current frame image includes camera
Spin matrix and camera translation vector.
4. according to the method described in claim 3, it is characterized in that, calculate the camera pose parameter of the current frame image,
Method is:
According to the imaging process of camera, the conic section is established and described to the intersection point of polar curve and the camera pose parameter
Camera spin matrix mathematical relationship, shown in the specific following formula of mathematical relationship:
According to the spatial relation of the marker and the camera, the camera pose parameter of the current frame image is calculated,
Shown in the following formula of specific computational methods:
Wherein, t indicates the translation vector of camera, s0、s1Indicate intermediate variable, r1Indicate the first row of camera spin matrix, m0
Indicate the origin image of world coordinate system, m1Indicate the label point image of marker, l∞Indicate described to polar curve, LxIndicate mark
Coordinate of the mark point of object in space coordinates, r11、r21、r31Corresponding element in camera spin matrix, (u are indicated respectively0,
v0) indicate m0Coordinate, (u1, v1) indicate m1Coordinate;
The spatial relation of the marker and shown camera is:The marker is located at camera front, the mark
The normal direction of plane is directed toward the camera where object.
5. according to the method described in claim 1, it is characterized in that, " the edge graph picture point for extracting the current frame image ",
Method is:
The edge graph picture point of the current frame image is extracted using edge detection algorithm.
6. according to the method described in claim 1, it is characterized in that, " calculating the current frame image based on the conic section
To polar curve ", method is:
When the quantity of the conic section is two, calculated according to quasi- affine-invariant features described to polar curve;
When the quantity of the conic section is one, original of the point as world coordinate system inside the conic section is extracted
Point, calculate the origin of the world coordinate system to polar curve, as the conic section to polar curve.
7. a kind of storage device, wherein being stored with a plurality of program, which is characterized in that described program is suitable for being loaded and being held by processor
The method of row vision positioning marker as claimed in any one of claims 1 to 6.
8. a kind of processing unit, including processor, storage device;Processor is adapted for carrying out each program;Storage device is suitable for
Store a plurality of program;It is characterized in that, described program is suitable for being loaded by processor and being executed as described in claim any one of 1-6
Vision positioning marker method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810118800.1A CN108447092B (en) | 2018-02-06 | 2018-02-06 | Method and device for visually positioning marker |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810118800.1A CN108447092B (en) | 2018-02-06 | 2018-02-06 | Method and device for visually positioning marker |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108447092A true CN108447092A (en) | 2018-08-24 |
CN108447092B CN108447092B (en) | 2020-07-28 |
Family
ID=63192012
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810118800.1A Active CN108447092B (en) | 2018-02-06 | 2018-02-06 | Method and device for visually positioning marker |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108447092B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111062233A (en) * | 2018-10-17 | 2020-04-24 | 北京地平线机器人技术研发有限公司 | Marker representation acquisition method, marker representation acquisition device and electronic equipment |
WO2021232222A1 (en) * | 2020-05-19 | 2021-11-25 | 华为技术有限公司 | Ranging method and apparatus |
CN116558504A (en) * | 2023-07-11 | 2023-08-08 | 之江实验室 | Monocular vision positioning method and device |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007025863A (en) * | 2005-07-13 | 2007-02-01 | Advanced Telecommunication Research Institute International | Photographing system, photographing method, and image processing program |
JP2008224641A (en) * | 2007-03-12 | 2008-09-25 | Masahiro Tomono | System for estimation of camera attitude |
CN103247048A (en) * | 2013-05-10 | 2013-08-14 | 东南大学 | Camera mixing calibration method based on quadratic curve and straight lines |
CN103258329A (en) * | 2013-05-24 | 2013-08-21 | 西安电子科技大学 | Camera calibration method based on one-dimensional feature of balls |
CN104517291A (en) * | 2014-12-15 | 2015-04-15 | 大连理工大学 | Pose measuring method based on coaxial circle characteristics of target |
CN105069809A (en) * | 2015-08-31 | 2015-11-18 | 中国科学院自动化研究所 | Camera positioning method and system based on planar mixed marker |
CN106558081A (en) * | 2016-11-28 | 2017-04-05 | 云南大学 | The method for demarcating the circular cone catadioptric video camera of optical resonator system |
-
2018
- 2018-02-06 CN CN201810118800.1A patent/CN108447092B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007025863A (en) * | 2005-07-13 | 2007-02-01 | Advanced Telecommunication Research Institute International | Photographing system, photographing method, and image processing program |
JP2008224641A (en) * | 2007-03-12 | 2008-09-25 | Masahiro Tomono | System for estimation of camera attitude |
CN103247048A (en) * | 2013-05-10 | 2013-08-14 | 东南大学 | Camera mixing calibration method based on quadratic curve and straight lines |
CN103258329A (en) * | 2013-05-24 | 2013-08-21 | 西安电子科技大学 | Camera calibration method based on one-dimensional feature of balls |
CN104517291A (en) * | 2014-12-15 | 2015-04-15 | 大连理工大学 | Pose measuring method based on coaxial circle characteristics of target |
CN105069809A (en) * | 2015-08-31 | 2015-11-18 | 中国科学院自动化研究所 | Camera positioning method and system based on planar mixed marker |
CN106558081A (en) * | 2016-11-28 | 2017-04-05 | 云南大学 | The method for demarcating the circular cone catadioptric video camera of optical resonator system |
Non-Patent Citations (3)
Title |
---|
WANG QI等: "Review on camera calibration", 《IEEE XPLORE》 * |
孟晓桥等: "一种新的基于圆环点的摄像机自标定方法", 《软件学报》 * |
张裕海: "多相机坐标测量技术的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111062233A (en) * | 2018-10-17 | 2020-04-24 | 北京地平线机器人技术研发有限公司 | Marker representation acquisition method, marker representation acquisition device and electronic equipment |
WO2021232222A1 (en) * | 2020-05-19 | 2021-11-25 | 华为技术有限公司 | Ranging method and apparatus |
CN116558504A (en) * | 2023-07-11 | 2023-08-08 | 之江实验室 | Monocular vision positioning method and device |
CN116558504B (en) * | 2023-07-11 | 2023-09-29 | 之江实验室 | Monocular vision positioning method and device |
Also Published As
Publication number | Publication date |
---|---|
CN108447092B (en) | 2020-07-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111199564B (en) | Indoor positioning method and device of intelligent mobile terminal and electronic equipment | |
CN110427905A (en) | Pedestrian tracting method, device and terminal | |
CN103729885B (en) | Various visual angles projection registers united Freehandhand-drawing scene three-dimensional modeling method with three-dimensional | |
CN108399386A (en) | Information extracting method in pie chart and device | |
CN112257676A (en) | Pointer instrument reading method and system and inspection robot | |
CN109636854A (en) | A kind of augmented reality three-dimensional Tracing Registration method based on LINE-MOD template matching | |
CN109598234A (en) | Critical point detection method and apparatus | |
CN109974721A (en) | A kind of vision winding detection method and device based on high-precision map | |
CN103854283A (en) | Mobile augmented reality tracking registration method based on online study | |
JP2016091108A (en) | Human body portion detection system and human body portion detection method | |
CN106709452B (en) | Instrument position detection method based on intelligent inspection robot | |
Vishal et al. | Accurate localization by fusing images and GPS signals | |
CN108447092A (en) | The method and device of vision positioning marker | |
CN108182695A (en) | Target following model training method and device, electronic equipment and storage medium | |
CN112634368A (en) | Method and device for generating space and OR graph model of scene target and electronic equipment | |
CN112634369A (en) | Space and or graph model generation method and device, electronic equipment and storage medium | |
CN106056121A (en) | Satellite assembly workpiece fast-identification method based on SIFT image feature matching | |
CN111191708A (en) | Automatic sample key point marking method, device and system | |
CN117333928B (en) | Face feature point detection method and device, electronic equipment and storage medium | |
Lin et al. | A comprehensive review of image line segment detection and description: Taxonomies, comparisons, and challenges | |
CN110160518A (en) | A kind of method for recognising star map towards microsatellite | |
CN115588196A (en) | Pointer type instrument reading method and device based on machine vision | |
CN104422441B (en) | A kind of electronic equipment and localization method | |
JP5975484B2 (en) | Image processing device | |
Gupta et al. | Image feature detection using an improved implementation of maximally stable extremal regions for augmented reality applications |
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 |