CN106991705A - A kind of location parameter method of estimation based on P3P algorithms - Google Patents
A kind of location parameter method of estimation based on P3P algorithms Download PDFInfo
- Publication number
- CN106991705A CN106991705A CN201710220035.XA CN201710220035A CN106991705A CN 106991705 A CN106991705 A CN 106991705A CN 201710220035 A CN201710220035 A CN 201710220035A CN 106991705 A CN106991705 A CN 106991705A
- Authority
- CN
- China
- Prior art keywords
- location parameter
- characteristic point
- camera
- characteristic
- characteristic points
- 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
Landscapes
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of location parameter method of estimation based on P3P algorithms, including step：The camera used demarcate obtaining camera parameter；Under the currently used pose of camera, 4 characteristic points in space are imaged and are obtained with the world coordinates and its image coordinate of 4 characteristic points；4 characteristic points are divided into two groups, using two characteristic points of diagonal position as public characteristic point, remaining 2 characteristic points are constituted into two groups of P3P characteristic points with public characteristic point respectively；According to the world coordinates and image coordinate of characteristic point in every group of P3P characteristic point, one group of real solution of public characteristic point location parameter is gone out using P3P Algorithm for Solving, the corresponding two groups of real solutions of two groups of P3P characteristic points are obtained；Chosen position parameter similarity is maximum from two groups of real solutions two solve and verified, and finally determine the location parameter of public characteristic point.By determining unique solution and unique solution being verified, to improve the efficiency and accuracy of location parameter resolving.
Description
Technical field
The present invention relates to a kind of location parameter method of estimation, more particularly to a kind of location parameter based on P3P algorithms is estimated
Meter method, belongs to technical field of computer vision.
Background technology
The pose estimation technique of view-based access control model is one of study hotspot in computer vision field, is vision positioning and leads
The important step of boat technology.The pose estimation technique of view-based access control model, captures Spatial Cooperation target image by camera, passes through image
Processing and pose algorithm for estimating solve camera pose parameter, and with moderate accuracy, cost is low, done using independent flexible and anti-electromagnetism
The characteristics of disturbing.
PnP algorithms are as conventional pose measuring method, and the individual points of the n known to relative position using in space (n >=3) are used as spy
Levy a little, by camera acquisition piece image, calculate posture information of the video camera relative to characteristic point.In actual applications, feature
Points are more, when occurring relative motion between camera and target, and characteristic point easily exceeds image scope, and characteristic point
There is mistake in matching, ultimately results in resolving failure.Therefore the feature points used are fewer, and resolving is more flexible, general to be calculated using P3P
Method and P4P algorithms.
Although P3P arithmetic accuracies are more or less the same with P4P arithmetic accuracies；But, P3P algorithms at most may be used according to 3 characteristic points
To calculate four groups of solutions, P4P algorithms can solve unique solution according to 4 characteristic points.However, image processing stage if there is
Some feature point extraction mistake, causes pose to resolve mistake, then the algorithm can not carry out self verification.Accordingly, it would be desirable to find one
Feature counts less, can determine unique solution and the pose computation that can be verified to unique solution needed for kind.
The content of the invention
It is a primary object of the present invention to overcoming deficiency of the prior art, there is provided a kind of position ginseng based on P3P algorithms
Number estimation method, not only computational efficiency is high, and can improve the accuracy of location parameter resolving, can be applied to close using separate type
Make goal directed unmanned aerial vehicle vision and feel land field.
In order to achieve the above object, the technical solution adopted in the present invention is：
A kind of location parameter method of estimation based on P3P algorithms, comprises the following steps：
1) camera used is demarcated, obtained in the camera intrinsic parameter for calculating camera internal reference exponential model, camera
Parameter includes the focal length and photocentre coordinate of camera；
2) under the currently used pose of camera, imaging is carried out to 4 characteristic points in space and obtains image, with 4
Any one characteristic point in individual characteristic point sets up world coordinate system for origin, and obtain 4 characteristic points world coordinates and its
Image coordinate in image；
3) 4 characteristic points are divided into two groups, two characteristic points using in 4 characteristic points positioned at diagonal position are used as public spy
Levy a little, remaining 2 characteristic points in 4 characteristic points are constituted to two sons for being respectively provided with 3 characteristic points with public characteristic point respectively
Collection, two subsets are two groups of P3P characteristic points；
4) according to the world coordinates and image coordinate of characteristic point in every group of P3P characteristic point, gone out using P3P Algorithm for Solving public
One group of real solution of characteristic point position parameter, obtains the corresponding two groups of real solutions of two groups of P3P characteristic points；
5) chosen position parameter similarity is maximum from two groups of real solutions two solve and verified, and finally determine public affairs
The location parameter of common characteristic point.
The present invention is further arranged to：The step 1) in demarcation use Zhang Zhengyou standardizations.
The present invention is further arranged to：The step 2) in 4 characteristic points to meet any 3 characteristic points not conllinear and 4
The requirement that individual characteristic point line assumes diamond in shape.
The present invention is further arranged to：The step 2) in 4 characteristic points of acquisition world coordinates and its in image
Image coordinate as in, specifically,
4 cooperative targets of separate type 2-1) are arranged in space, and the center of each cooperative target represents a characteristic point,
Then have 4 characteristic points；
World coordinate system 2-2) is set up using any one characteristic point in 4 characteristic points as origin, measures special by instrument
Levy world coordinates a little；
2-3) using the camera for having demarcated focal length, under the currently used pose of camera, cooperative target is imaged
Obtain image；
Image processing method 2-4) is utilized, the image of characteristic point is extracted in the image of the cooperative target gathered from camera
Coordinate.
The present invention is further arranged to：The instrument includes tape measure and total powerstation.
The present invention is further arranged to：The step 4) in the corresponding two groups of real solutions of two groups of P3P characteristic points of acquisition, tool
Body is,
One group of P3P characteristic point 4-1) is chosen, according to camera national forest park in Xiaokeng, camera internal reference exponential model and Camera extrinsic number
3 characteristic points are as follows on the relational expression of world coordinates and camera coordinates in this group of P3P characteristic point of model construction,
(C2-C1)T(C2-C1)=(P2-P1)T(P2-P1)
(C3-C1)T(C3-C1)=(P3-P1)T(P3-P1)
(C3-C1)T(C2-C1)=(P3-P1)T(P2-P1)
Wherein, C1、C2、C3The camera coordinates of 3 characteristic points, P in respectively this group P3P characteristic point1、P2、P3Respectively should
The world coordinates of 3 characteristic points in group P3P characteristic points；
4-2) by step 1) obtained camera parameter and step 2) world coordinates of characteristic point that obtains and its image coordinate
In the relational expression for being updated to world coordinates and camera coordinates, three constraint equations for obtaining P3P models are,
Wherein, λ1、λ2、d1It is unknown number to be solved, θ1、θ2、θ3Respectively camera photocentre is pointed to 3 in this group of P3P characteristic point
Angle between 3 vectors that individual characteristic point is constituted；
Trigonometric function exchange entry 4-3) is utilized, intermediate variable x, y is introduced, passes through λ1=x+cos θ1And λ2=y+cos θ2Come
Simplify constraint equation, change into the unary biquadratic equation on x, solve all real solutions of x；
Public characteristic point coordinates under corresponding x many solutions, the camera coordinates system of solution is that location parameter has many solutions, often
The location parameter for the public characteristic point that one group of P3P characteristic point is solved is that 4 solutions are following；
The number of the solution of the location parameter of the public characteristic point of one group of P3P characteristic point 4-4) is designated as m, m≤4, it is i-th
Solution is designated as Ai, i ∈ [1, m]；The number of the solution of the location parameter of the public characteristic point of another group of P3P characteristic point is designated as n, n≤
4, its j-th of solution is designated as Bj, j ∈ [1, n].
The present invention is further arranged to：The step 5) chosen position parameter similarity is maximum from two groups of real solutions two
It is individual to solve and verified, the location parameter of public characteristic point is finally determined, specifically,
The location parameter similarity ρ (i, j) in two groups of real solutions 5-1) is calculated, calculation formula is,
Wherein,Respectively by Ai、BjThe one-dimensional vector being rewritten into；
5-2) set location parameter similarity threshold, has according to location parameter of the public characteristic point under camera coordinates system
The characteristics of uniqueness, two maximum solutions of location parameter similarity in two groups of real solutions are chosen, and this two solutions and position are joined
Number similarity threshold is verified；
If its location parameter similarity is more than location parameter similarity threshold, assert that location parameter is resolved correct, choose
The location parameter of public characteristic point is directly used to navigate by the average value of two solutions as the location parameter of public characteristic point；It is no
Then, assert that location parameter resolves mistake, gather next two field picture repeat step 2) arrive step 5).
Compared with prior art, the invention has the advantages that：
A kind of location parameter method of estimation based on P3P algorithms that the present invention is improved, by setting public characteristic point to constitute
Two groups of P3P characteristic points determine true value, and improved by effectively simplifying constraint equation real-time that location parameter is estimated and
Stability, the problem of overcoming many solutions and low computational efficiency of P3P algorithms；Meanwhile, it is determined that on the basis of unique solution, passing through meter
The location parameter similarity for calculating different solutions adds the link of a verification to position parametric solution result, to improve location parameter solution
The accuracy of calculation, is allowed to have more engineering practicability.
The above is only the general introduction of technical solution of the present invention, in order to be better understood upon the technological means of the present invention, under
With reference to accompanying drawing, the invention will be further described in face.
Brief description of the drawings
Fig. 1 is the position view of 4 characteristic points of the embodiment of the present invention；
Fig. 2 is the schematic diagram of the P3P algorithm models of the embodiment of the present invention.
Embodiment
With reference to Figure of description, the present invention is further illustrated.
The present invention provides a kind of location parameter method of estimation based on P3P algorithms, comprises the following steps：
1) camera used is demarcated, obtained in the camera intrinsic parameter for calculating camera internal reference exponential model, camera
Parameter includes the focal length and photocentre coordinate of camera；Demarcation therein uses Zhang Zhengyou standardizations, i.e. Zhang Shi standardizations.
2) under the currently used pose of camera, imaging is carried out to 4 characteristic points in space and obtains image, with 4
Any one characteristic point in individual characteristic point sets up world coordinate system for origin, and obtain 4 characteristic points world coordinates and its
Image coordinate in image；Wherein, 4 characteristic points meet any 3 characteristic points not conllinear and 4 characteristic point lines
The requirement assumed diamond in shape, as shown in Figure 1.
Specifically,
4 cooperative targets of separate type 2-1) are arranged in space, and the center of each cooperative target represents a characteristic point,
Then have 4 characteristic points；
World coordinate system 2-2) is set up using any one characteristic point in 4 characteristic points as origin O, passes through tape measure and whole station
The instruments such as instrument measure the world coordinates of characteristic point；
2-3) using the camera for having demarcated focal length, under the currently used pose of camera, cooperative target is imaged
Obtain image；
Image processing method 2-4) is utilized, the image of characteristic point is extracted in the image of the cooperative target gathered from camera
Coordinate.
3) 4 characteristic points are divided into two groups, two characteristic points using in 4 characteristic points positioned at diagonal position are used as public spy
Levy a little, remaining 2 characteristic points in 4 characteristic points are constituted to two sons for being respectively provided with 3 characteristic points with public characteristic point respectively
Collection, two subsets are two groups of P3P characteristic points.
4) according to the world coordinates and image coordinate of characteristic point in every group of P3P characteristic point, gone out using P3P Algorithm for Solving public
One group of real solution of characteristic point position parameter, obtains the corresponding two groups of real solutions of two groups of P3P characteristic points；
Specifically,
One group of P3P characteristic point 4-1) is chosen, according to camera national forest park in Xiaokeng, camera internal reference exponential model and outer parameter model
Build 3 characteristic points in this group of P3P characteristic point as follows on the relational expression of world coordinates and camera coordinates,
(C2-C1)T(C2-C1)=(P2-P1)T(P2-P1)
(C3-C1)T(C3-C1)=(P3-P1)T(P3-P1)
(C3-C1)T(C2-C1)=(P3-P1)T(P2-P1)
Wherein, C1、C2、C3The camera coordinates of 3 characteristic points in respectively this group P3P characteristic point, camera coordinates are according to step
2) the characteristic point image coordinate and step 1 obtained in) camera parameter obtained by calibrating calculating obtains, P1、P2、P3The respectively group
The world coordinates of 3 characteristic points in P3P characteristic points；
4-2) by step 1) obtained camera parameter and step 2) world coordinates of characteristic point that obtains and its image coordinate
In the relational expression for being updated to world coordinates and camera coordinates, three constraint equations for obtaining P3P models are,
Wherein, λ1、λ2、d1It is unknown number, θ1、θ2、θ3Respectively camera photocentre points to 3 spies in this group of P3P characteristic point
The angle between 3 a little constituted vectors is levied, it is vector in the P3P algorithm model schematic diagrames shown in Fig. 2With
WithWithBetween angle；
Trigonometric function exchange entry 4-3) is utilized, intermediate variable x, y is introduced, passes through λ1=x+cos θ1And λ2=y+cos θ2Come
Simplify constraint equation, change into the unary biquadratic equation on x, solve all real solutions of x；
Public characteristic point coordinates under corresponding x many solutions, the camera coordinates system of solution is that location parameter has many solutions, often
The location parameter for the public characteristic point that one group of P3P characteristic point is solved is that 4 solutions are following；
The number of the solution of the location parameter of the public characteristic point of one group of P3P characteristic point 4-4) is designated as m, m≤4, it is i-th
Solution is designated as Ai, i ∈ [1, m]；The number of the solution of the location parameter of the public characteristic point of another group of P3P characteristic point is designated as n, n≤
4, its j-th of solution is designated as Bj, j ∈ [1, n].
5) chosen position parameter similarity is maximum from two groups of real solutions two solve and verified, and finally determine public affairs
The location parameter of common characteristic point；
Specifically,
The location parameter similarity ρ (i, j) in two groups of real solutions 5-1) is calculated, calculation formula is,
Wherein,Respectively by Ai、BjThe one-dimensional vector being rewritten into；
5-2) set location parameter similarity threshold, has according to location parameter of the public characteristic point under camera coordinates system
The characteristics of uniqueness, two maximum solutions of location parameter similarity in two groups of real solutions are chosen, and this two solutions and position are joined
Number similarity threshold is verified；
If its location parameter similarity is more than location parameter similarity threshold, assert that location parameter is resolved correct, choose
The location parameter of public characteristic point is directly used to navigate by the average value of two solutions as the location parameter of public characteristic point；It is no
Then, assert that location parameter resolves mistake, gather next two field picture repeat step 2) arrive step 5).
The innovative point of the present invention is, in the case of there are many solutions based on P3P Algorithm for Solving pose, by determining unique solution
And unique solution is verified, to improve the efficiency and accuracy of location parameter resolving.
General principle, principal character and the advantage of the present invention has been shown and described above.The technical staff of the industry should
Understand, the present invention is not limited to the above embodiments, the original for simply illustrating the present invention described in above-described embodiment and specification
Reason, without departing from the spirit and scope of the present invention, various changes and modifications of the present invention are possible, these changes and improvements
It all fall within the protetion scope of the claimed invention.The claimed scope of the invention is by appended claims and its equivalent circle
It is fixed.
Claims (7)
1. a kind of location parameter method of estimation based on P3P algorithms, it is characterised in that comprise the following steps：
1) camera used is demarcated, obtains the camera intrinsic parameter for calculating camera internal reference exponential model, camera intrinsic parameter
Focal length and photocentre coordinate including camera；
2) under the currently used pose of camera, imaging is carried out to 4 characteristic points in space and obtains image, with 4 spies
Any one characteristic point in levying a little sets up world coordinate system for origin, and obtain 4 characteristic points world coordinates and its into
As the image coordinate in image；
3) 4 characteristic points are divided into two groups, two characteristic points using in 4 characteristic points positioned at diagonal position are used as public characteristic
Point, remaining 2 characteristic points in 4 characteristic points is constituted with public characteristic point respectively two subsets for being respectively provided with 3 characteristic points,
Two subsets are two groups of P3P characteristic points；
4) according to the world coordinates and image coordinate of characteristic point in every group of P3P characteristic point, public characteristic is gone out using P3P Algorithm for Solving
One group of real solution of point location parameter, obtains the corresponding two groups of real solutions of two groups of P3P characteristic points；
5) chosen position parameter similarity is maximum from two groups of real solutions two solve and verified, and finally determine public spy
Levy location parameter a little.
2. a kind of location parameter method of estimation based on P3P algorithms according to claim 1, it is characterised in that：The step
It is rapid 1) in demarcation use Zhang Zhengyou standardizations.
3. a kind of location parameter method of estimation based on P3P algorithms according to claim 1, it is characterised in that：The step
It is rapid 2) in 4 characteristic points meet the requirement that any 3 characteristic points are not conllinear and 4 characteristic point lines assume diamond in shape.
4. a kind of location parameter method of estimation based on P3P algorithms according to claim 1, it is characterised in that：The step
It is rapid 2) in 4 characteristic points of acquisition world coordinates and its image coordinate in image, specifically,
4 cooperative targets of separate type 2-1) are arranged in space, and the center of each cooperative target represents a characteristic point, then altogether
There are 4 characteristic points；
World coordinate system 2-2) is set up using any one characteristic point in 4 characteristic points as origin, characteristic point is measured by instrument
World coordinates；
2-3) using the camera for having demarcated focal length, under the currently used pose of camera, imaging acquisition is carried out to cooperative target
Image；
Image processing method 2-4) is utilized, the image that characteristic point is extracted in the image of the cooperative target gathered from camera is sat
Mark.
5. a kind of location parameter method of estimation based on P3P algorithms according to claim 4, it is characterised in that：The work
Tool includes tape measure and total powerstation.
6. a kind of location parameter method of estimation based on P3P algorithms according to claim 1, it is characterised in that：The step
It is rapid 4) in the corresponding two groups of real solutions of two groups of P3P characteristic points of acquisition, specifically, 4-1) choose one group of P3P characteristic point, according to phase
Machine national forest park in Xiaokeng, camera internal reference exponential model and Camera extrinsic exponential model build in this group of P3P characteristic point 3 characteristic points on
The relational expression of world coordinates and camera coordinates is as follows,
(C2-C1)T(C2-C1)=(P2-P1)T(P2-P1)
(C3-C1)T(C3-C1)=(P3-P1)T(P3-P1)
(C3-C1)T(C2-C1)=(P3-P1)T(P2-P1)
Wherein, C1、C2、C3The camera coordinates of 3 characteristic points, P in respectively this group P3P characteristic point1、P2、P3Respectively this group P3P
The world coordinates of 3 characteristic points in characteristic point；
4-2) by step 1) obtained camera parameter and step 2) world coordinates of characteristic point that obtains and its image coordinate substitute into
Into the relational expression of world coordinates and camera coordinates, three constraint equations for obtaining P3P models are,
d1 2(λ1 2-2λ1cosθ1+ 1)=(P2-P1)T(P2-P1)
d1 2(λ2 2-2λ2cosθ2+ 1)=(P3-P1)T(P3-P1)
d1 2(λ1λ2cosθ3-λ1cosθ1-λ2cosθ2+ 1)=(P3-P1)T(P2-P1)
Wherein, λ1、λ2、d1It is unknown number to be solved, θ1、θ2、θ3Respectively camera photocentre points to 3 spies in this group of P3P characteristic point
Levy the angle between 3 a little constituted vectors；
Trigonometric function exchange entry 4-3) is utilized, intermediate variable x, y is introduced, passes through λ1=x+cos θ1And λ2=y+cos θ2To simplify about
Shu Fangcheng, changes into the unary biquadratic equation on x, solves all real solutions of x；
Public characteristic point coordinates under corresponding x many solutions, the camera coordinates system of solution is that location parameter has many solutions, each group
The location parameter for the public characteristic point that P3P characteristic points are solved is that 4 solutions are following；
The number of the solution of the location parameter of the public characteristic point of one group of P3P characteristic point 4-4) is designated as m, m≤4, its i-th solution note
For Ai, i ∈ [1, m]；The number of the solution of the location parameter of the public characteristic point of another group of P3P characteristic point is designated as n, n≤4, its
J-th of solution is designated as Bj, j ∈ [1, n].
7. a kind of location parameter method of estimation based on P3P algorithms according to claim 6, it is characterised in that：The step
Chosen position parameter similarity is maximum from two groups of real solutions two rapid 5) solve and verified, and finally determine public characteristic
The location parameter of point, specifically,
The location parameter similarity ρ (i, j) in two groups of real solutions 5-1) is calculated, calculation formula is,
Wherein,Respectively by Ai、BjThe one-dimensional vector being rewritten into；
5-2) set location parameter similarity threshold, has unique according to location parameter of the public characteristic point under camera coordinates system
Property the characteristics of, choose two maximum solutions of location parameter similarity in two groups of real solutions, and by this two solutions and location parameter phase
Verified like degree threshold value；
If its location parameter similarity is more than location parameter similarity threshold, assert that location parameter is resolved correct, choose two
The location parameter of public characteristic point is directly used to navigate by the average value of solution as the location parameter of public characteristic point；Otherwise, recognize
Location parameter resolves mistake, gathers next two field picture repeat step 2) arrive step 5).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710220035.XA CN106991705B (en) | 2017-04-06 | 2017-04-06 | Position parameter estimation method based on P3P algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710220035.XA CN106991705B (en) | 2017-04-06 | 2017-04-06 | Position parameter estimation method based on P3P algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106991705A true CN106991705A (en) | 2017-07-28 |
| CN106991705B CN106991705B (en) | 2020-03-10 |
Family
ID=59414740
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710220035.XA Expired - Fee Related CN106991705B (en) | 2017-04-06 | 2017-04-06 | Position parameter estimation method based on P3P algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106991705B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110500954A (en) * | 2019-07-30 | 2019-11-26 | 中国地质大学（武汉） | A kind of aircraft pose measuring method based on circle feature and P3P algorithm |
| CN110689575A (en) * | 2019-09-29 | 2020-01-14 | 百度在线网络技术（北京）有限公司 | Image collector calibration method, device, equipment and medium |
| CN111667539A (en) * | 2020-06-08 | 2020-09-15 | 武汉唯理科技有限公司 | Camera calibration and plane measurement method |
| CN111932611A (en) * | 2020-05-26 | 2020-11-13 | 北京百度网讯科技有限公司 | Object position acquisition method and device |
| CN112150546A (en) * | 2020-10-23 | 2020-12-29 | 西华大学 | Monocular vision pose estimation method based on auxiliary point geometric constraint |
| CN116310126A (en) * | 2023-03-23 | 2023-06-23 | 南京航空航天大学 | Aircraft air inlet three-dimensional reconstruction method and system based on cooperative targets |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104656097A (en) * | 2015-01-28 | 2015-05-27 | 武汉理工大学 | Calibration device based on rotary type two-dimensional laser three-dimensional reconstruction system |
| CN104677340A (en) * | 2013-11-30 | 2015-06-03 | 中国科学院沈阳自动化研究所 | Point character based monocular vision pose measurement method |
| CN105809702A (en) * | 2016-03-29 | 2016-07-27 | 南京航空航天大学 | Improved position and orientation estimation method based on Tsai algorism |
-
2017
- 2017-04-06 CN CN201710220035.XA patent/CN106991705B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104677340A (en) * | 2013-11-30 | 2015-06-03 | 中国科学院沈阳自动化研究所 | Point character based monocular vision pose measurement method |
| CN104656097A (en) * | 2015-01-28 | 2015-05-27 | 武汉理工大学 | Calibration device based on rotary type two-dimensional laser three-dimensional reconstruction system |
| CN105809702A (en) * | 2016-03-29 | 2016-07-27 | 南京航空航天大学 | Improved position and orientation estimation method based on Tsai algorism |
Non-Patent Citations (2)
| Title |
|---|
| WANG TING ET AL.: "Some Discussion on the Conditions of the Unique Solution of P3P Problem", 《2006 INTERNATIONAL CONFERENCE ON MECHATRONICS AND AUTOMATION》 * |
| YINGMING HAO ET AL.: "Robust analysis of P3P pose estimation", 《2007 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND BIOMIMETICS (ROBIO)》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110500954A (en) * | 2019-07-30 | 2019-11-26 | 中国地质大学（武汉） | A kind of aircraft pose measuring method based on circle feature and P3P algorithm |
| CN110689575A (en) * | 2019-09-29 | 2020-01-14 | 百度在线网络技术（北京）有限公司 | Image collector calibration method, device, equipment and medium |
| CN110689575B (en) * | 2019-09-29 | 2022-04-22 | 阿波罗智联(北京)科技有限公司 | Image collector calibration method, device, equipment and medium |
| CN111932611A (en) * | 2020-05-26 | 2020-11-13 | 北京百度网讯科技有限公司 | Object position acquisition method and device |
| CN111932611B (en) * | 2020-05-26 | 2024-05-10 | 阿波罗智联(北京)科技有限公司 | Object position acquisition method and device |
| CN111667539A (en) * | 2020-06-08 | 2020-09-15 | 武汉唯理科技有限公司 | Camera calibration and plane measurement method |
| CN111667539B (en) * | 2020-06-08 | 2023-08-29 | 武汉唯理科技有限公司 | Camera calibration and plane measurement method |
| CN112150546A (en) * | 2020-10-23 | 2020-12-29 | 西华大学 | Monocular vision pose estimation method based on auxiliary point geometric constraint |
| CN112150546B (en) * | 2020-10-23 | 2023-11-21 | 西华大学 | Monocular vision pose estimation method based on auxiliary point geometric constraint |
| CN116310126A (en) * | 2023-03-23 | 2023-06-23 | 南京航空航天大学 | Aircraft air inlet three-dimensional reconstruction method and system based on cooperative targets |
| CN116310126B (en) * | 2023-03-23 | 2023-11-03 | 南京航空航天大学 | Aircraft air inlet three-dimensional reconstruction method and system based on cooperative targets |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106991705B (en) | 2020-03-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106991705A (en) | A kind of location parameter method of estimation based on P3P algorithms | |
| CN111354042B (en) | Feature extraction method and device of robot visual image, robot and medium | |
| CN105469405B (en) | Positioning and map constructing method while view-based access control model ranging | |
| CN104121902B (en) | Implementation method of indoor robot visual odometer based on Xtion camera | |
| CN111145232A (en) | Three-dimensional point cloud automatic registration method based on characteristic information change degree | |
| CN105354841B (en) | A kind of rapid remote sensing image matching method and system | |
| CN106919944A (en) | A kind of wide-angle image method for quickly identifying based on ORB algorithms | |
| CN108510551A (en) | Method and system for calibrating camera parameters under long-distance large-field-of-view condition | |
| Shi et al. | A visual circle based image registration algorithm for optical and SAR imagery | |
| CN107729893A (en) | A kind of vision positioning method of clapper die spotting press, system and storage medium | |
| CN105184786B (en) | A kind of floating type triangle character describes method | |
| CN112883850B (en) | Multi-view space remote sensing image matching method based on convolutional neural network | |
| CN112946679B (en) | Unmanned aerial vehicle mapping jelly effect detection method and system based on artificial intelligence | |
| CN107240130A (en) | Remote Sensing Image Matching method, apparatus and system | |
| CN106056121A (en) | Satellite assembly workpiece fast-identification method based on SIFT image feature matching | |
| CN108320310B (en) | Image sequence-based space target three-dimensional attitude estimation method | |
| CN108036786A (en) | Position and posture detection method, device and computer-readable recording medium based on auxiliary line | |
| CN110033492A (en) | Camera marking method and terminal | |
| Kostavelis et al. | Visual odometry for autonomous robot navigation through efficient outlier rejection | |
| CN113706635B (en) | Long-focus camera calibration method based on point feature and line feature fusion | |
| Deng et al. | Accurate and flexible calibration method for a class of visual sensor networks | |
| CN114529615A (en) | Radar calibration method, device and storage medium | |
| CN111583342A (en) | Target rapid positioning method and device based on binocular vision | |
| CN113221805B (en) | Method and device for acquiring image position of power equipment | |
| CN112418251B (en) | Infrared body temperature detection method and system |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200310 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |