CN113570660B - Shooting device pose estimation method, device, computer equipment and storage medium - Google Patents

Shooting device pose estimation method, device, computer equipment and storage medium Download PDF

Info

Publication number
CN113570660B
CN113570660B CN202110706712.5A CN202110706712A CN113570660B CN 113570660 B CN113570660 B CN 113570660B CN 202110706712 A CN202110706712 A CN 202110706712A CN 113570660 B CN113570660 B CN 113570660B
Authority
CN
China
Prior art keywords
coordinate system
control point
point
determining
shooting device
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
Application number
CN202110706712.5A
Other languages
Chinese (zh)
Other versions
CN113570660A (en
Inventor
孟强
谢朝毅
谢亮
付伟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Insta360 Innovation Technology Co Ltd
Original Assignee
Insta360 Innovation Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Insta360 Innovation Technology Co Ltd filed Critical Insta360 Innovation Technology Co Ltd
Priority to CN202110706712.5A priority Critical patent/CN113570660B/en
Publication of CN113570660A publication Critical patent/CN113570660A/en
Application granted granted Critical
Publication of CN113570660B publication Critical patent/CN113570660B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
    • G06F17/12—Simultaneous equations, e.g. systems of linear equations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration

Abstract

The application relates to a shooting device pose estimation method, a shooting device pose estimation device, computer equipment and a storage medium. The method comprises the following steps: determining a control point under a world coordinate system and a first linear coefficient for linearly showing the three-dimensional point by the control point under the world coordinate system by performing principal component analysis on the obtained three-dimensional point; further determining a second linear representation of the control point in the camera coordinate system; and solving a corresponding linear equation set by the second linear table, determining the base and distance constraint of a zero space of the control point under the coordinate of the shooting device, determining the coordinate of the control point under the coordinate of the shooting device, and determining the pose coordinate transformation from the world coordinate system to the coordinate system of the shooting device according to the coordinate of the control point under the coordinate of the shooting device and the coordinate of the control point under the world coordinate system. The method can improve the data processing efficiency on the basis of ensuring the stability and the precision of data processing.

Description

Shooting device pose estimation method, device, computer equipment and storage medium
Technical Field
The present disclosure relates to the field of computer vision, and in particular, to a method and apparatus for estimating pose of a photographing device, a computer device, and a storage medium.
Background
Shooting device Pose estimation (Pose estimation) plays a very important role in the field of computer vision. The accuracy of the pose estimation method of the shooting device directly influences the finishing quality of tasks such as visual tracking, photogrammetry, shooting device calibration and the like in the field of computer visual research.
The camera pose estimation, i.e., PNP (global-n-Point), problem is a problem of calculating coordinate transformation from a world coordinate system to a camera coordinate system by coordinate values of n 3D points in the world coordinate system and 2D coordinate values of the n 3D points projected on a unit focal plane (or unit sphere) of the camera.
When solving the problem of pose estimation of a shooting device, algorithms such as P3P (Perselect-3-Point), DLT (direct Linear transformation), EPNP, UPNP, MRE and the like are usually adopted for implementation; when the EPNP algorithm is used for solving the problem of pose estimation of the shooting device in the prior art, high stability and high precision can be ensured, but the data processing efficiency is very low.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a shooting device pose estimation method, device, computer apparatus, and storage medium that can improve the data processing efficiency of shooting device pose estimation while ensuring the stability and accuracy of calculating the shooting device pose estimation.
A photographing apparatus pose estimation method, the method comprising:
acquiring three-dimensional points under a world coordinate system;
determining a control point under the world coordinate system by performing principal component analysis on the three-dimensional points;
determining a first linear coefficient of each three-dimensional point linearly represented by the control point in a world coordinate system and a coordinate point of each three-dimensional point linearly represented by each control point in the world coordinate system;
determining that the projection point is represented by a second linearity of the control point under the coordinate system of the shooting device according to the first linearity representation coefficient, the coordinate point and the projection point corresponding to the coordinate point under the coordinate system of the shooting device; solving a corresponding homogeneous linear equation set of the second linear table to determine the base and distance constraint of the control point in the zero space under the coordinates of the shooting device;
determining control point coordinates of the corresponding control points under the coordinates of the shooting device according to the zero-space base and the distance constraint;
and determining pose coordinate transformation from the world coordinate system to the shooting device coordinate system according to the control point coordinates of the control points under the shooting device coordinates and the control point coordinates of the control points under the world coordinate system.
In one embodiment, the determining the first linear coefficient of each three-dimensional point linearly represented by the control point in the world coordinate system and the coordinate point of each three-dimensional point linearly represented by each control point in the world coordinate system includes:
determining a first linear representation of each three-dimensional point by each control point linear representation according to the first linear representation coefficients;
and determining coordinate points of each three-dimensional point linearly represented by each control point in the world coordinate system according to the first linear representation.
In one embodiment, the determining, according to the first linear representation coefficient, the coordinate point, and the projection point corresponding to the coordinate point in the camera coordinate system, the projection point is represented by a second linear representation of the control point in the camera coordinate system includes:
determining a position relation expression satisfied by the coordinate point and the projection point according to the coordinate point and the projection point corresponding to the coordinate point under a coordinate system of a shooting device;
and determining that each projection point is linearly represented by a second linear representation of the control point under the coordinate system of the shooting device according to the position relation and the first linear representation.
In one embodiment, the determining, by analyzing the second linear equation set corresponding to the second linear table, a base and a distance constraint of a corresponding zero space of the control point under the coordinates of the photographing device includes:
determining the second linear table to form a corresponding homogeneous linear equation set according to a projection model of the shooting device;
and analyzing the homogeneous linear equation according to the linear constraint by establishing the linear constraint of the control point under the coordinate system of the shooting device, and determining the base and distance constraint of the control point corresponding to the zero space under the coordinate system of the shooting device.
In one embodiment, the determining the control point coordinates of the corresponding control point under the camera coordinates according to the zero-space base and the distance constraint includes:
determining a nonlinear equation set according to the control point linear table determined by the zero-space basis and the distance constraint;
solving the nonlinear equation set to obtain a linear representation coefficient of a corresponding zero-space base pair control point;
and determining the corresponding control point coordinates of the control point under the coordinates of the shooting device according to the linear representation coefficient of the zero-space base pair control point.
In one embodiment, the determining the control point under the world coordinate system by performing principal component analysis on the three-dimensional point includes:
performing principal component analysis on the three-dimensional points to obtain gravity center points and three-dimensional vectors corresponding to the three-dimensional points;
and carrying out weighting processing on the three-dimensional vector according to the gravity center point, and determining a control point under the world coordinate system.
In one embodiment, the determining the pose coordinate transformation from the world coordinate system to the camera coordinate system according to the control point coordinates of the control point under the camera coordinate and the control point coordinates of the control point under the world coordinate system includes:
determining a first control point coordinate system of the control point determined based on the shooting device coordinate system according to the control point coordinate of the control point under the shooting device coordinate;
determining a second control point coordinate system of the control point determined based on the shooting device coordinate system according to the control point coordinate of the control point under the world coordinate system;
and determining pose coordinate transformation from the world coordinate system to the shooting device coordinate system according to the first control point coordinate system and the second control point coordinate system.
A photographing apparatus pose estimation apparatus, the apparatus comprising:
the acquisition module is used for acquiring three-dimensional points under the world coordinate system;
the analysis module is used for determining a control point under the world coordinate system by performing principal component analysis on the three-dimensional points;
the first determining module is used for determining a first linear coefficient of each three-dimensional point linearly represented by the control point in the world coordinate system and a coordinate point of each three-dimensional point linearly represented by each control point in the world coordinate system;
the second determining module is used for determining that the projection point is represented by a second linearity of the control point under the coordinate system of the shooting device according to the first linearity representation coefficient, the coordinate point and the projection point corresponding to the coordinate point under the coordinate system of the shooting device;
the data processing module is used for determining the basis and distance constraint of the control point in the zero space under the coordinates of the shooting device by solving the corresponding homogeneous linear equation set of the second linear table;
the third determining module is used for determining control point coordinates of the corresponding control point under the coordinates of the shooting device according to the zero-space base and the distance constraint;
And the fourth determining module is used for determining pose coordinate transformation from the world coordinate system to the shooting device coordinate system according to the control point coordinates of the control points under the shooting device coordinates and the control point coordinates of the control points under the world coordinate system.
A computer device comprising a memory storing a computer program and a processor which when executing the computer program performs the steps of:
acquiring three-dimensional points under a world coordinate system;
determining a control point under the world coordinate system by performing principal component analysis on the three-dimensional points;
determining a first linear coefficient of each three-dimensional point linearly represented by the control point in a world coordinate system and a coordinate point of each three-dimensional point linearly represented by each control point in the world coordinate system;
determining that the projection point is represented by a second linearity of the control point under the coordinate system of the shooting device according to the first linearity representation coefficient, the coordinate point and the projection point corresponding to the coordinate point under the coordinate system of the shooting device; solving a corresponding homogeneous linear equation set of the second linear table to determine the base and distance constraint of the control point in the zero space under the coordinates of the shooting device;
Determining control point coordinates of the corresponding control points under the coordinates of the shooting device according to the zero-space base and the distance constraint;
and determining pose coordinate transformation from the world coordinate system to the shooting device coordinate system according to the control point coordinates of the control points under the shooting device coordinates and the control point coordinates of the control points under the world coordinate system.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
acquiring three-dimensional points under a world coordinate system;
determining a control point under the world coordinate system by performing principal component analysis on the three-dimensional points;
determining a first linear coefficient of each three-dimensional point linearly represented by the control point in a world coordinate system and a coordinate point of each three-dimensional point linearly represented by each control point in the world coordinate system;
determining that the projection point is represented by a second linearity of the control point under the coordinate system of the shooting device according to the first linearity representation coefficient, the coordinate point and the projection point corresponding to the coordinate point under the coordinate system of the shooting device; solving a corresponding homogeneous linear equation set of the second linear table to determine the base and distance constraint of the control point in the zero space under the coordinates of the shooting device;
Determining control point coordinates of the corresponding control points under the coordinates of the shooting device according to the zero-space base and the distance constraint;
and determining pose coordinate transformation from the world coordinate system to the shooting device coordinate system according to the control point coordinates of the control points under the shooting device coordinates and the control point coordinates of the control points under the world coordinate system.
The shooting device pose estimation method, the shooting device pose estimation device, the computer equipment and the storage medium acquire principal component analysis of three-dimensional points in a world coordinate system, determine control points in the world coordinate system and determine first linear coefficients of the three-dimensional points, which are linearly represented by the control points in the world coordinate system, according to the control points; determining a three-dimensional point projection point according to the first linear representation coefficient, wherein the three-dimensional point projection point is represented by a second linear representation of a control point under a coordinate system of the shooting device; solving a corresponding linear equation set of the second linear table to determine a zero-space basis of the control point under the coordinates of the shooting device; determining control point coordinates of the corresponding control points under the coordinates of the shooting device according to the zero-space basis; further determining pose coordinate transformation from the world coordinate system to the shooting device coordinate system; the pose coordinate transformation from the world coordinate system to the shooting device coordinate system is determined by solving the basis of the zero space of the linear equation set calculation control point, and the data processing efficiency is improved by reducing the calculated amount of data on the basis of ensuring the stability and the precision of data processing.
Drawings
FIG. 1 is an application environment diagram of a shooting device pose estimation method in one embodiment;
FIG. 2 is a flowchart of a method for estimating pose of a photographing apparatus according to an embodiment;
FIG. 3 is a flow diagram of a method of determining the base and distance constraints of the null space of a control point in one embodiment;
FIG. 4 is a flowchart of a method for determining coordinates of a control point in a coordinate system of a camera according to an embodiment;
fig. 5 is a block diagram showing a configuration of a photographing apparatus pose estimation apparatus in one embodiment;
fig. 6 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The shooting device pose estimation method provided by the application can be applied to an application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The terminal acquires three-dimensional points under a world coordinate system from a server; determining control points under a world coordinate system by performing principal component analysis on the three-dimensional points; determining a first linear coefficient of each three-dimensional point linearly represented by a control coordinate point in a world coordinate system; according to the first linear representation coefficient, the coordinate point and the projection point corresponding to the coordinate point under the coordinate system of the shooting device, determining the three-dimensional point projection point to be represented by a second linear representation of the control coordinate point under the coordinate system of the shooting device; the coordinate position relation is determined according to world coordinates of the three-dimensional point under a world coordinate system and shooting device coordinates of the three-dimensional point projection point under a shooting device coordinate system; solving a corresponding linear equation set of the second linear table to determine a zero-space basis of the control point under the coordinates of the shooting device; determining control point coordinates of the corresponding control points under the coordinates of the shooting device according to the zero-space basis; and determining pose coordinate transformation from the world coordinate system to the shooting device coordinate system according to the control point coordinates of the control points under the shooting device coordinates and the control point coordinates of the control points under the world coordinate system. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smartphones, tablet computers and portable wearable devices, and the server 104 may be implemented by a stand-alone server or a server cluster formed by a plurality of servers; the photographing device may be any photographing apparatus with a camera, such as a mobile phone, a camera, a video camera, a robot, a drone, etc., which is not limited in the present invention.
In one embodiment, as shown in fig. 2, a method for estimating pose of a photographing device is provided, and the method is applied to the terminal in fig. 1 for illustration, and includes the following steps:
step 202, three-dimensional points in a world coordinate system are acquired.
The number of three-dimensional points is N (N > =4), N is a positive integer, that is, N three-dimensional points are obtained from the server and input to the terminal.
Step 204, determining control points in the world coordinate system by performing principal component analysis on the three-dimensional points.
The principal component analysis is to perform weighted averaging on known three-dimensional column vectors, determine corresponding gravity center points (namely, the gravity center is the average value of all three-dimensional vectors), subtract the gravity center points from each three-dimensional vector, solve a covariance matrix, and obtain a characteristic value and a characteristic vector of the covariance matrix through singular value decomposition; determining control points according to the feature vectors and the gravity center points, wherein the number of the control points is 4; the resulting 4 control points can be expressed as
Specifically, principal component analysis is performed on the three-dimensional points, so that gravity center points and three-dimensional vectors corresponding to the three-dimensional points are obtained; calculating control points through a singular value decomposition (Singular Value Decomposition, SVD) method, weighting three-dimensional vectors according to gravity points, and determining control points under a world coordinate system; for example, n three-dimensional column vectors v i Center of gravity of pairIs thatv i And->Representing three-dimensional column vectors, the addition being a vector addition; subtracting the gravity centers from all the three-dimensional vectors, calculating a covariance matrix, performing svd decomposition to obtain feature vectors, adding the three-dimensional vectors to the gravity center points to obtain three-dimensional points, and taking the three-dimensional points and the gravity center points as control points; the specific calculation process of the control point is implemented through an SVD algorithm, which is not described in detail herein.
In step 206, a first linear coefficient of each three-dimensional point linearly represented by the control point in the world coordinate system and a coordinate point of each three-dimensional point linearly represented by each control point in the world coordinate system are determined.
Specifically, a first linear representation expression of the three-dimensional points, which is linearly represented by control points in a world coordinate system, is obtained, the weighted sum relation is converted into an expression form of homogeneous coordinates according to the weighted sum relation satisfied between the control points and the three-dimensional points, a first linear representation coefficient of the first linear representation expression is determined by solving the expression form of the homogeneous coordinates, the first linear representation is determined according to the first linear representation coefficient, and coordinate points, which are linearly represented by all the control points in the world coordinate system, of all the three-dimensional points are determined according to the first linear representation. The three-dimensional points are linearly represented by control points in the world coordinate system in the conventional manner, and are not described herein.
And step 208, determining that the projection point is represented by a second linearity of the control point under the coordinate system of the shooting device according to the first linearity representation coefficient, the coordinate point and the projection point corresponding to the coordinate point under the coordinate system of the shooting device.
Wherein, according to the first linear representation coefficient, the coordinate points of the three-dimensional points which are linearly represented by the control points in the world coordinate system can be obtainedAnd +.>Projection point in camera coordinate system +.>According to->And->The coordinates of the coordinate points can determine a positional relationship satisfied between the two, and can be expressed as: />R is three-dimensional point and is defined by each control point line under world coordinate systemAnd a rotation matrix between the coordinate points shown by the character table and the projection points under the coordinate system of the shooting device, wherein T is a translation matrix between the coordinate points of the three-dimensional points linearly shown by the control points under the coordinate system of the world and the projection points under the coordinate system of the shooting device.
And 210, determining the base and distance constraint of the control point in the zero space under the coordinates of the shooting device by solving a corresponding linear equation set of the second linear table.
The distance constraint refers to a preset relationship between any two control points among the control points. Specifically, the control points are respectively according to 4 control points in the world coordinate system And->According to the functional relationship->And a first linear representation->(wherein->α ki To express coefficients) can be determined to obtain the three-dimensional point projection points expressed by a second linearity of 4 control points under the coordinate system of the shooting device as follows:
and resolving and solving the second linear table according to the projection model of the shooting device to obtain a linear equation set corresponding to the second linear table, establishing linear constraint of a control point under the coordinate system of the shooting device according to the linear equation set, and determining a zero-space basis corresponding to the control point under the coordinate system of the shooting device. I.e. set upi=1, 2,3,4. Then there is
Establishing a linear constraint on the coordinates of the control point in the coordinate system of the shooting device according to the linear equation set as follows:
is provided with
The values of the basis that yields the null space for the four control points are:
where, null space (Null space) refers to the original image space where the image is zero, i.e., { x|ax=0 }. For example, if the matrix is a, null (a) is used to represent the Null space of a; the base of the null space, i.e. the rank of the matrix.
And 212, determining the control point coordinates of the corresponding control point under the coordinates of the shooting device according to the zero-space base and the distance constraint.
Specifically, a homogeneous linear equation set is established according to the projection relation of the shooting device, and the distance constraint of a group of bases and control points of the zero space of the homogeneous linear equation set under the coordinate system of the shooting device is solved; linearly showing the control points according to a group of bases of the null space, and obtaining a nonlinear equation set according to the obtained distance constraint; and calculating the coordinates of the corresponding control point under the coordinate system of the shooting device according to the linear representation coefficient of the zero-space basis pair control point by solving the linear representation coefficient of the zero-space basis pair control point of the nonlinear equation set.
Step 214, determining pose coordinate transformation from the world coordinate system to the camera coordinate system according to the control point coordinates of the control point under the camera coordinate and the control point coordinates of the control point under the world coordinate system.
Specifically, coordinate transformation from a control point of the world coordinate system to a control point of the photographing device coordinate system is calculated by using a nearest neighbor point iterative method (Iterative Closest Point, ICP), that is, a first control point coordinate system of the control point determined based on the photographing device coordinate system is determined according to the control point coordinate of the control point under the photographing device coordinate; determining a second control point coordinate system of the control point determined based on the camera coordinate system according to the control point coordinate of the control point under the world coordinate system; and determining pose coordinate transformation from the world coordinate system to the camera coordinate system according to the first control point coordinate system and the second control point coordinate system, wherein the coordinate transformation from the world coordinate system to the camera coordinate system calculated by the nearest neighbor point iteration method is the prior art, and details are not repeated here.
According to the shooting device pose estimation method, the three-dimensional points in the world coordinate system are obtained to perform principal component analysis, the control points in the world coordinate system are determined, and the first linear coefficients of the three-dimensional points, which are linearly represented by the control points in the world coordinate system, are determined according to the control points; determining a three-dimensional point projection point according to the first linear representation coefficient, wherein the three-dimensional point projection point is represented by a second linear representation of a control point under a coordinate system of the shooting device; solving a corresponding linear equation set of the second linear table to determine a zero-space basis of the control point under the coordinates of the shooting device; determining control point coordinates of the corresponding control points under the coordinates of the shooting device according to the zero-space basis and the distance constraint; determining pose coordinate transformation from a world coordinate system to a shooting device coordinate system according to control point coordinates of the control points under the shooting device coordinates and control point coordinates of the control points under the world coordinate system; namely, stability of data processing is determined by solving a linear equation set and accuracy and processing efficiency of data are determined by reducing the calculation amount of data.
In one embodiment, as shown in fig. 3, a method for estimating pose of a photographing device is provided, and the method is applied to the terminal in fig. 1 for illustration, and includes the following steps:
in step 302, each three-dimensional point is determined to be represented by a first linear representation of the control point based on the first linear representation coefficients.
Wherein, the first linear representation means that three-dimensional points are represented by 4 control points in a world coordinate system. The first linear representation coefficient is determined by matrix transformation by satisfying a functional relation among the first matrix, the gravity center point, the orthogonal matrix and the upper triangular matrix. The first matrix is obtained by performing a decentration process on the input three-dimensional points.
According to the functional relation satisfied by the defined control points:
inputting three-dimensional point P i The first linear table of all control points in the world coordinate system is shown as:α ki to express the coefficient, +.>Is the point corresponding to the control point in the world coordinate system.
According to the first matrix, the gravity center point, the orthogonal matrix and the upper triangular matrix, the functional relation is satisfied:
determining a first apparent coefficient alpha ij Where i=1, 2,3,4, j=1, l, n, i.e. the first tabulated coefficient is:
where j=1, l, n.
Step 304, determining coordinate points of each three-dimensional point linearly represented by each control point in the world coordinate system according to the first linear table.
And 306, determining a position relation formula which is satisfied by the coordinate points and the projection points according to the coordinate points and the projection points corresponding to the coordinate points in the coordinate system of the photographing device.
In step 308, each projection point is determined to be linearly represented by a second linear representation of the control point in the camera coordinate system according to the positional relationship and the first linear representation.
In particular, according to the coordinates of three-dimensional points in the world coordinate systemAnd coordinates of the three-dimensional point in the camera coordinate system +.>The functional relationship of (2) can be expressed as: />First linear representation +.>Determining the decentered three-dimensional point projection point from the second linear representation of the control point in the camera coordinate system>Is a point corresponding to the control point in the camera coordinate system.
Step 310, determining a second linear table to represent a corresponding homogeneous linear equation set according to the projection model of the camera.
The projection model of the photographing device is an existing model, and will not be described herein.
Specifically, the control point is expressed as in the camera coordinate systemi＝1，2，3，4。/>The i point represents the coordinate of the X axis under the coordinate of the shooting device, Y i c Representing the coordinate of the Y-axis in the camera coordinate, < >>Representing the Z-axis coordinate at the camera coordinates,
then there isThus, the corresponding system of linear equations can be determined to be +. >
In step 312, by establishing a linear constraint of the control point in the camera coordinate system, the linear constraint is analyzed according to the linear constraint alignment linear equation, and a base and a distance constraint of the control point in the corresponding zero space in the camera coordinate system are determined.
Specifically, by establishing linear constraint of a control point under a coordinate system of a shooting device, analyzing a linear equation according to the linear constraint, and determining base and distance constraint of a corresponding zero space of the control point under the coordinate system of the shooting device; the linear constraint of the control point coordinates under the established shooting device coordinate system is as follows:
is provided with
The values of the resulting zero-space basis are:
the distance constraint obtained is:
in the method for determining the zero-space basis corresponding to the control point under the coordinate of the shooting device, the first linear representation of the control point according to the three-dimensional point determines the second linear representation of the control point under the coordinate system of the shooting device, the second linear representation corresponding to the linear equation set is determined according to the projection model of the shooting device, and the linear constraint of the control point under the coordinate system of the shooting device is established, so that the zero-space basis corresponding to the control point under the coordinate of the shooting device is determined, the Gaussian elimination method is utilized to determine the zero-space basis, the performance of an algorithm is improved on the basis of ensuring stability, and the processing efficiency of data is further improved.
In one embodiment, as shown in fig. 4, a method for determining coordinates of a control point in a coordinate system of a photographing device is provided, and the method is applied to the terminal in fig. 1 for illustration, and includes the following steps:
step 402, a system of nonlinear equations is determined from the control point linear table and the distance constraint determined from the basis of the null space.
And step 404, solving a nonlinear equation set to obtain a linear representation coefficient of the corresponding zero-space base pair control point.
And step 406, determining the control point coordinates of the corresponding control point under the coordinates of the shooting device according to the linear representation coefficients of the zero-space base pair control points.
Specifically, a homogeneous linear equation set is established according to the projection relation of the shooting device, and a distance constraint of a group of bases and control points of a zero space under the coordinate system of the shooting device is obtained by solving the homogeneous linear equation set; determining a linear representation of the control point according to a set of bases of the null space, and obtaining a set of nonlinear equations according to the distance constraint; the coefficients are expressed by solving the linear relation control points from the nonlinear equation set to the zero space; and calculating the coordinates of the corresponding control points under the coordinate system of the shooting device according to the tabulated coefficients. I.e. obtaining homogeneous linear equation set mx=o 2n×1 According to the four groups of zero-space basisAnd 6 groups of distance constraint of the control points, and converting the homogeneous linear equation set to obtain a corresponding nonlinear equation set by simplifying the distance constraint; and solving a nonlinear equation set by adopting a Gaussian Newton method to obtain the coordinates of the control point in the coordinate system of the shooting device. I.e. obtain mx=o 2n×1 Four sets of zero space bases:
where j=1, 2,3,4.
Where M has an infinite set of bases in the zero space, and 4 in the dimension, each set of bases has four linearly independent 12-dimensional vectors as its bases. The four control points constitute a 12-dimensional vector, which should theoretically belong to the zero space of M, so the 12-dimensional vector composed of the four sets of control points should be a linear combination of four linearly independent vectors in a set of bases of the zero space.
The 6 sets of distance constraints obtained are:
according toSimplifying the distance constraint to obtain:
wherein,u.ltoreq.v and i.ltoreq.j. The corresponding nonlinear equation set is obtained as follows:
by the GaussNewton methodSolving the nonlinear equation set, determining a linear representation coefficient of a base pair control point of a zero space in coordinates of the control point in a coordinate system of the shooting device, and determining the coordinates of the control point in the coordinate system of the shooting device; i.e. by determining the linear representation coefficient lambda of the base pair control point of the null space of the coordinates of the 4 control points in the camera coordinate system 1 ，λ 2 ，λ 3 ，λ 4 Lambda is taken as 1 ，λ 2 ，λ 3 ，λ 4 Substitution into(i=1, 2,3, 4) determining coordinates of the control point at the camera coordinates.
In the method for determining the control point coordinates under the coordinate system of the shooting device, the homogeneous linear equation set is established according to the projection relation, and the distance constraint of a group of bases and control points of the zero space of the homogeneous linear equation set under the coordinate system of the shooting device is solved; obtaining a group of nonlinear equation sets according to the linear table of the control points and the distance constraint; the coefficients are expressed by solving the linear relation control points from the nonlinear equation set to the zero space; calculating the coordinates of the corresponding control points under the coordinate system of the shooting device according to the tabulated coefficients; on the basis of ensuring the data precision, the data processing steps are reduced, and the processing efficiency of the algorithm is improved.
It should be understood that, although the steps in the flowcharts of fig. 2-4 are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in fig. 2-4 may include multiple steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor does the order in which the steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of the steps or stages in other steps or other steps.
In one embodiment, as shown in fig. 5, there is provided a photographing apparatus pose estimation apparatus including: the acquisition module 502, the analysis module 504, the first determination module 506, the second determination module 508, the data processing module 510, the third determination module 512, and the fourth determination module 514, wherein:
an acquisition module 502 is configured to acquire a three-dimensional point in a world coordinate system.
The analysis module 504 is configured to determine a control point in the world coordinate system by performing principal component analysis on the three-dimensional point.
The first determining module 506 is configured to determine a first linear coefficient of each three-dimensional point linearly represented by a control point in the world coordinate system, and a coordinate point of each three-dimensional point linearly represented by each control point in the world coordinate system.
The second determining module 508 is configured to determine that the projected point is represented by a second linearity of the control point under the coordinate system of the photographing device according to the first linearity representation coefficient, the coordinate point, and the projected point corresponding to the coordinate point under the coordinate system of the photographing device.
The data processing module 510 is configured to determine a base and a distance constraint of a null space of the control point under the coordinates of the photographing device by solving a homogeneous linear equation set corresponding to the second linear representation.
A third determining module 512 is configured to determine control point coordinates of the corresponding control point under the camera coordinates according to the base of the null space and the distance constraint.
A fourth determining module 514 is configured to determine pose coordinate transformation from the world coordinate system to the camera coordinate system according to the control point coordinates of the control point under the camera coordinate and the control point coordinates of the control point under the world coordinate system.
The shooting device pose estimation device is used for determining control points under the world coordinate system by acquiring principal component analysis of three-dimensional points under the world coordinate system and determining first linear coefficients of the three-dimensional points, which are linearly represented by the control points under the world coordinate system, according to the control points; determining a three-dimensional point projection point according to the first linear representation coefficient, wherein the three-dimensional point projection point is represented by a second linear representation of a control point under a coordinate system of the shooting device; solving a corresponding linear equation set of the second linear table to determine a zero-space basis of the control point under the coordinates of the shooting device; determining control point coordinates of the corresponding control points under the coordinates of the shooting device according to the zero-space basis and the distance constraint; determining pose coordinate transformation from a world coordinate system to a shooting device coordinate system according to control point coordinates of the control points under the shooting device coordinates and control point coordinates of the control points under the world coordinate system; namely, stability of data processing is determined by solving a linear equation set and accuracy and processing efficiency of data are determined by reducing the calculation amount of data.
In another embodiment, a capturing apparatus pose estimation apparatus is provided, which includes, in addition to the acquisition module 502, the analysis module 504, the first determination module 506, the second determination module 508, the data processing module 510, the third determination module 512, and the fourth determination module 514: the device comprises a conversion module, a solving module and a weighting processing module, wherein:
in one embodiment, the first determining module 506 is further configured to determine, according to the first linear representation coefficient, a first linear representation of each three-dimensional point linearly represented by each control point; and determining coordinate points of each three-dimensional point linearly represented by each control point in the world coordinate system according to the first linear representation.
In one embodiment, the first determining module 506 is further configured to determine, according to the coordinate point and a projection point corresponding to the coordinate point in the coordinate system of the photographing device, a positional relationship that the coordinate point and the projection point satisfy; and determining a second linear representation of each projection point by the control point in the coordinate system of the shooting device according to the position relation and the first linear representation.
In one embodiment, the data processing module 510 is further configured to determine, according to the projection model of the camera, a second linear table to represent a corresponding homogeneous linear equation set; analyzing a linear constraint of a control point under a coordinate system of the shooting device according to a linear constraint alignment linear equation, and determining a base and a distance constraint of the control point corresponding to a zero space under the coordinate system of the shooting device; a system of nonlinear equations is determined based on the control point linear representation and the distance constraint determined from the basis of the null space.
And the solving module is used for solving the nonlinear equation set to obtain the linear representation coefficient of the corresponding zero-space base pair control point.
In one embodiment, the third determining module 512 is further configured to determine the control point coordinates of the corresponding control point under the camera coordinates according to the linear table coefficient of the base pair control point in the null space.
In one embodiment, the analysis module 504 is further configured to obtain a gravity center point and a three-dimensional vector corresponding to the three-dimensional point by performing principal component analysis on the three-dimensional point.
And the weighting processing module is used for carrying out weighting processing on the three-dimensional vector according to the gravity center point and determining a control point under the world coordinate system.
In one embodiment, the fourth determining module 514 is further configured to determine a first control point coordinate system of the control points determined based on the camera coordinate system according to the control point coordinates of the control points under the camera coordinates; determining a second control point coordinate system of the control point determined based on the camera coordinate system according to the control point coordinate of the control point under the world coordinate system; and determining pose coordinate transformation from the world coordinate system to the shooting device coordinate system according to the first control point coordinate system and the second control point coordinate system.
In one embodiment, a gravity center point and a three-dimensional vector corresponding to the three-dimensional point are obtained by acquiring the three-dimensional point under the world coordinate system and performing principal component analysis on the three-dimensional point; weighting the three-dimensional vector according to the gravity center point to determine a control point under the world coordinate system; determining a first linear coefficient of each three-dimensional point linearly represented by a control point in the world coordinate system, and determining that each three-dimensional point is linearly represented by the control point in the world coordinate system according to the first linear coefficient; according to the coordinate position relation and the first linear representation, determining that the three-dimensional point projection point is represented by a second linear representation of a control point under the coordinate system of the shooting device; determining a second linear table to show a corresponding linear equation set according to the projection model of the shooting device; and (3) analyzing the linear equation according to the linear constraint by establishing the linear constraint of the control point under the coordinate system of the shooting device, and determining the base and distance constraint of the control point corresponding to the zero space under the coordinate system of the shooting device.
Converting the linear equation set according to the zero-space basis to obtain a corresponding homogeneous linear equation set; obtaining the zero space base of the homogeneous linear equation set and the distance constraint of the control point under the coordinate system of the shooting device; according to the zero space base and the distance constraint, aligning the linear equation set for conversion to obtain a corresponding nonlinear equation set; solving a nonlinear equation set to obtain a linear representation coefficient of a corresponding zero-space base pair control point; determining control point coordinates of the corresponding control point under the coordinates of the shooting device according to the linear representation coefficients of the control points of the zero-space basis pairs; determining a first control point coordinate system of the control point determined based on the shooting device coordinate system according to the control point coordinate of the control point under the shooting device coordinate; determining a second control point coordinate system of the control point determined based on the camera coordinate system according to the control point coordinate of the control point under the world coordinate system; according to the first control point coordinate system and the second control point coordinate system, pose coordinate transformation from the world coordinate system to the shooting device coordinate system is determined, the basis of a zero space is determined by solving a linear equation set, the accuracy and the calculation stability of data are ensured, and the processing efficiency of the data is improved by reducing the calculation amount of the data.
For specific limitations of the imaging apparatus pose estimation apparatus, reference may be made to the above limitations of the imaging apparatus pose estimation method, and no further description is given here. The above-described respective modules in the imaging apparatus pose estimation apparatus may be implemented in whole or in part by software, hardware, or a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a terminal, and the internal structure of which may be as shown in fig. 6. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The computer program, when executed by a processor, implements a photographing apparatus pose estimation method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in fig. 6 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:
acquiring three-dimensional points under a world coordinate system;
determining control points under a world coordinate system by performing principal component analysis on the three-dimensional points;
determining a first linear coefficient of each three-dimensional point linearly represented by a control point in the world coordinate system and a coordinate point of each three-dimensional point linearly represented by each control point in the world coordinate system;
determining that the projection point is represented by a second linearity of the control point under the coordinate system of the shooting device according to the first linearity representation coefficient, the coordinate point and the projection point corresponding to the coordinate point under the coordinate system of the shooting device; solving a corresponding homogeneous linear equation set by the second linear table, and determining the base and distance constraint of the control point in the zero space under the coordinates of the shooting device;
Determining control point coordinates of the corresponding control points under the coordinates of the shooting device according to the zero-space basis and the distance constraint;
and determining pose coordinate transformation from the world coordinate system to the shooting device coordinate system according to the control point coordinates of the control points under the shooting device coordinates and the control point coordinates of the control points under the world coordinate system.
In one embodiment, the processor when executing the computer program further performs the steps of:
determining a first linear representation of each three-dimensional point by the linear representation of each control point according to the first linear representation coefficients;
and determining coordinate points of each three-dimensional point linearly represented by each control point in the world coordinate system according to the first linear representation.
In one embodiment, the processor when executing the computer program further performs the steps of:
determining a position relation expression satisfied by the coordinate point and the projection point according to the coordinate point and the projection point corresponding to the coordinate point under the coordinate system of the shooting device;
and determining a second linear representation of each projection point by the control point in the coordinate system of the shooting device according to the position relation and the first linear representation.
In one embodiment, the processor when executing the computer program further performs the steps of:
determining a second linear table to form a corresponding homogeneous linear equation set according to the projection model of the shooting device;
And (3) establishing linear constraint of the control point under the coordinate system of the shooting device, analyzing according to the linear constraint alignment linear equation, and determining the base and distance constraint of the control point corresponding to the zero space under the coordinate system of the shooting device.
In one embodiment, the processor when executing the computer program further performs the steps of:
converting the linear equation set according to the zero-space basis to obtain a corresponding homogeneous linear equation set;
obtaining the zero space base of the homogeneous linear equation set and the distance constraint of the control point under the coordinate system of the shooting device;
according to the zero space base and the distance constraint, aligning the linear equation set for conversion to obtain a corresponding nonlinear equation set;
solving a nonlinear equation set to obtain a linear representation coefficient of a corresponding zero-space base pair control point;
and determining the control point coordinates of the corresponding control point under the coordinates of the shooting device according to the linear representation coefficients of the control points of the zero-space basis pair.
In one embodiment, the processor when executing the computer program further performs the steps of:
the principal component analysis is carried out on the three-dimensional points, so that a gravity center point and a three-dimensional vector corresponding to the three-dimensional points are obtained;
and carrying out weighting processing on the three-dimensional vector according to the gravity center point, and determining a control point under the world coordinate system.
In one embodiment, the processor when executing the computer program further performs the steps of:
determining a first control point coordinate system of the control point determined based on the shooting device coordinate system according to the control point coordinate of the control point under the shooting device coordinate;
determining a second control point coordinate system of the control point determined based on the camera coordinate system according to the control point coordinate of the control point under the world coordinate system;
and determining pose coordinate transformation from the world coordinate system to the shooting device coordinate system according to the first control point coordinate system and the second control point coordinate system.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring three-dimensional points under a world coordinate system;
determining control points under a world coordinate system by performing principal component analysis on the three-dimensional points;
determining a first linear coefficient of each three-dimensional point linearly represented by a control point in the world coordinate system and a coordinate point of each three-dimensional point linearly represented by each control point in the world coordinate system;
determining that the projection point is represented by a second linearity of the control point under the coordinate system of the shooting device according to the first linearity representation coefficient, the coordinate point and the projection point corresponding to the coordinate point under the coordinate system of the shooting device; solving a corresponding homogeneous linear equation set by the second linear table, and determining the base and distance constraint of the control point in the zero space under the coordinates of the shooting device;
Determining control point coordinates of the corresponding control points under the coordinates of the shooting device according to the zero-space basis and the distance constraint;
and determining pose coordinate transformation from the world coordinate system to the shooting device coordinate system according to the control point coordinates of the control points under the shooting device coordinates and the control point coordinates of the control points under the world coordinate system.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining a first linear representation of each three-dimensional point by the linear representation of each control point according to the first linear representation coefficients;
and determining coordinate points of each three-dimensional point linearly represented by each control point in the world coordinate system according to the first linear representation.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining a position relation expression satisfied by the coordinate point and the projection point according to the coordinate point and the projection point corresponding to the coordinate point under the coordinate system of the shooting device;
and determining a second linear representation of each projection point by the control point in the coordinate system of the shooting device according to the position relation and the first linear representation.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining a second linear table to form a corresponding homogeneous linear equation set according to the projection model of the shooting device;
And (3) establishing linear constraint of the control point under the coordinate system of the shooting device, analyzing according to the linear constraint alignment linear equation, and determining the base and distance constraint of the control point corresponding to the zero space under the coordinate system of the shooting device.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining a nonlinear equation set according to the control point linear representation and the distance constraint determined by the zero-space basis;
solving a nonlinear equation set to obtain a linear representation coefficient of a corresponding zero-space base pair control point;
and determining the control point coordinates of the corresponding control point under the coordinates of the shooting device according to the linear representation coefficients of the control points of the zero-space basis pair.
In one embodiment, the computer program when executed by the processor further performs the steps of:
the principal component analysis is carried out on the three-dimensional points, so that a gravity center point and a three-dimensional vector corresponding to the three-dimensional points are obtained;
and carrying out weighting processing on the three-dimensional vector according to the gravity center point, and determining a control point under the world coordinate system.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining a first control point coordinate system of the control point determined based on the shooting device coordinate system according to the control point coordinate of the control point under the shooting device coordinate;
Determining a second control point coordinate system of the control point determined based on the camera coordinate system according to the control point coordinate of the control point under the world coordinate system;
and determining pose coordinate transformation from the world coordinate system to the shooting device coordinate system according to the first control point coordinate system and the second control point coordinate system.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, or the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.

Claims (10)

1. A shooting device pose estimation method, characterized in that the method comprises:
acquiring three-dimensional points under a world coordinate system;
determining a control point under the world coordinate system by performing principal component analysis on the three-dimensional points;
determining a first linear representation coefficient of each three-dimensional point linearly represented by the control point in a world coordinate system and a coordinate point of each three-dimensional point linearly represented by each control point in the world coordinate system;
Determining that the projection point is represented by a second linearity of the control point under the coordinate system of the shooting device according to the first linearity representation coefficient, the coordinate point and the projection point corresponding to the coordinate point under the coordinate system of the shooting device; solving a corresponding homogeneous linear equation set of the second linear table to determine the base and distance constraint of the control point in the zero space under the coordinates of the shooting device;
determining control point coordinates of the corresponding control points under the coordinates of the shooting device according to the zero-space base and the distance constraint;
and determining pose coordinate transformation from the world coordinate system to the shooting device coordinate system according to the control point coordinates of the control points under the shooting device coordinates and the control point coordinates of the control points under the world coordinate system.
2. The method of claim 1, wherein said determining a first linear representation coefficient for each of said three-dimensional points linearly represented by said control points in the world coordinate system and a coordinate point for each of said three-dimensional points linearly represented by each of said control points in the world coordinate system comprises:
determining a first linear representation of each three-dimensional point by each control point linear representation according to the first linear representation coefficients;
And determining coordinate points of each three-dimensional point linearly represented by each control point in the world coordinate system according to the first linear representation.
3. The method of claim 2, wherein determining the projected point from the first linear representation coefficient, the coordinate point, and the projected point corresponding to the coordinate point in the camera coordinate system, the projected point being represented by a second linear representation of the control point in the camera coordinate system, comprises:
determining a position relation expression satisfied by the coordinate point and the projection point according to the coordinate point and the projection point corresponding to the coordinate point under a coordinate system of a shooting device;
and determining that each projection point is linearly represented by a second linear representation of the control point under the coordinate system of the shooting device according to the position relation and the first linear representation.
4. The method of claim 1, wherein determining the base and distance constraints of the corresponding null space of the control point at the camera coordinates by resolving the second set of linear equations that represent the corresponding homogeneous system of linear equations comprises:
determining the second linear table to form a corresponding homogeneous linear equation set according to a projection model of the shooting device;
And analyzing the homogeneous linear equation according to the linear constraint by establishing the linear constraint of the control point under the coordinate system of the shooting device, and determining the base and distance constraint of the control point corresponding to the zero space under the coordinate system of the shooting device.
5. The method of claim 4, wherein the determining control point coordinates of the corresponding control point at camera coordinates based on the zero-space basis and the distance constraint comprises:
determining a nonlinear equation set according to the control point linear table determined by the zero-space basis and the distance constraint;
solving the nonlinear equation set to obtain a linear representation coefficient of a corresponding zero-space base pair control point;
and determining the corresponding control point coordinates of the control point under the coordinates of the shooting device according to the linear representation coefficient of the zero-space base pair control point.
6. The method of claim 1, wherein said determining control points in said world coordinate system by principal component analysis of said three-dimensional points comprises:
performing principal component analysis on the three-dimensional points to obtain gravity center points and three-dimensional vectors corresponding to the three-dimensional points;
And carrying out weighting processing on the three-dimensional vector according to the gravity center point, and determining a control point under the world coordinate system.
7. The method of claim 1, wherein determining a pose coordinate transformation of the world coordinate system to the camera coordinate system based on the control point coordinates of the control point in the camera coordinate system and the control point coordinates of the control point in the world coordinate system comprises:
determining a first control point coordinate system of the control point determined based on the shooting device coordinate system according to the control point coordinate of the control point under the shooting device coordinate;
determining a second control point coordinate system of the control point determined based on the shooting device coordinate system according to the control point coordinate of the control point under the world coordinate system;
and determining pose coordinate transformation from the world coordinate system to the shooting device coordinate system according to the first control point coordinate system and the second control point coordinate system.
8. A photographing apparatus pose estimation apparatus, characterized in that the apparatus comprises:
the acquisition module is used for acquiring three-dimensional points under the world coordinate system;
the analysis module is used for determining a control point under the world coordinate system by performing principal component analysis on the three-dimensional points;
The first determining module is used for determining a first linear representation coefficient of each three-dimensional point linearly represented by the control point in the world coordinate system and a coordinate point of each three-dimensional point linearly represented by each control point in the world coordinate system;
the second determining module is used for determining that the projection point is represented by a second linearity of the control point under the coordinate system of the shooting device according to the first linearity representation coefficient, the coordinate point and the projection point corresponding to the coordinate point under the coordinate system of the shooting device;
the data processing module is used for determining the basis and distance constraint of the control point in the zero space under the coordinates of the shooting device by solving the corresponding homogeneous linear equation set of the second linear table;
the third determining module is used for determining control point coordinates of the corresponding control point under the coordinates of the shooting device according to the zero-space base and the distance constraint;
and the fourth determining module is used for determining pose coordinate transformation from the world coordinate system to the shooting device coordinate system according to the control point coordinates of the control points under the shooting device coordinates and the control point coordinates of the control points under the world coordinate system.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.
CN202110706712.5A 2021-06-24 2021-06-24 Shooting device pose estimation method, device, computer equipment and storage medium Active CN113570660B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110706712.5A CN113570660B (en) 2021-06-24 2021-06-24 Shooting device pose estimation method, device, computer equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110706712.5A CN113570660B (en) 2021-06-24 2021-06-24 Shooting device pose estimation method, device, computer equipment and storage medium

Publications (2)

Publication Number Publication Date
CN113570660A CN113570660A (en) 2021-10-29
CN113570660B true CN113570660B (en) 2024-04-16

Family

ID=78162702

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110706712.5A Active CN113570660B (en) 2021-06-24 2021-06-24 Shooting device pose estimation method, device, computer equipment and storage medium

Country Status (1)

Country Link
CN (1) CN113570660B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112150546A (en) * 2020-10-23 2020-12-29 西华大学 Monocular vision pose estimation method based on auxiliary point geometric constraint
CN113012226A (en) * 2021-03-22 2021-06-22 浙江商汤科技开发有限公司 Camera pose estimation method and device, electronic equipment and computer storage medium

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112150546A (en) * 2020-10-23 2020-12-29 西华大学 Monocular vision pose estimation method based on auxiliary point geometric constraint
CN113012226A (en) * 2021-03-22 2021-06-22 浙江商汤科技开发有限公司 Camera pose estimation method and device, electronic equipment and computer storage medium

Also Published As

Publication number Publication date
CN113570660A (en) 2021-10-29

Similar Documents

Publication Publication Date Title
US20210110599A1 (en) Depth camera-based three-dimensional reconstruction method and apparatus, device, and storage medium
WO2019205852A1 (en) Method and apparatus for determining pose of image capture device, and storage medium therefor
CN112328715B (en) Visual positioning method, training method of related model, related device and equipment
CN113256718B (en) Positioning method and device, equipment and storage medium
US20230237683A1 (en) Model generation method and apparatus based on multi-view panoramic image
CN112435193A (en) Method and device for denoising point cloud data, storage medium and electronic equipment
CN111325792A (en) Method, apparatus, device, and medium for determining camera pose
CN113361365A (en) Positioning method and device, equipment and storage medium
CN113570659B (en) Shooting device pose estimation method, device, computer equipment and storage medium
CN110807798B (en) Image recognition method, system, related device and computer readable storage medium
CN113298870B (en) Object posture tracking method and device, terminal equipment and storage medium
US11514645B2 (en) Electronic device for providing visual localization based on outdoor three-dimension map information and operating method thereof
CN112197708B (en) Measuring method and device, electronic device and storage medium
CN113570660B (en) Shooting device pose estimation method, device, computer equipment and storage medium
CN113436269B (en) Image dense stereo matching method, device and computer equipment
CN110956131A (en) Single-target tracking method, device and system
CN116912467A (en) Image stitching method, device, equipment and storage medium
CN115294280A (en) Three-dimensional reconstruction method, apparatus, device, storage medium, and program product
CN115042184A (en) Robot hand-eye coordinate conversion method and device, computer equipment and storage medium
CN112615993A (en) Depth information acquisition method, binocular camera module, storage medium and electronic equipment
CN113808050B (en) Denoising method, device and equipment for 3D point cloud and storage medium
CN114750147B (en) Space pose determining method and device of robot and robot
CN115100286B (en) Unmanned aerial vehicle acquisition viewpoint determining method and device, computer equipment and storage medium
CN117994334A (en) Pose estimation method and device of shooting equipment, computer equipment and storage medium
CN113596336B (en) Image acquisition method and device, electronic equipment and storage medium

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