CN110490940A - Camera calibration method and apparatus based on gridiron pattern single image - Google Patents
Camera calibration method and apparatus based on gridiron pattern single image Download PDFInfo
- Publication number
- CN110490940A CN110490940A CN201910755404.4A CN201910755404A CN110490940A CN 110490940 A CN110490940 A CN 110490940A CN 201910755404 A CN201910755404 A CN 201910755404A CN 110490940 A CN110490940 A CN 110490940A
- Authority
- CN
- China
- Prior art keywords
- camera
- gridiron pattern
- parameter
- angle point
- angle
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 96
- 238000012937 correction Methods 0.000 claims description 28
- 230000006870 function Effects 0.000 claims description 25
- 238000013519 translation Methods 0.000 claims description 23
- 238000003860 storage Methods 0.000 claims description 9
- 230000005055 memory storage Effects 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 16
- 230000008569 process Effects 0.000 description 10
- 238000003384 imaging method Methods 0.000 description 9
- 238000012545 processing Methods 0.000 description 7
- 238000006243 chemical reaction Methods 0.000 description 6
- 230000009466 transformation Effects 0.000 description 6
- 238000004590 computer program Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 241000208340 Araliaceae Species 0.000 description 3
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 3
- 235000003140 Panax quinquefolius Nutrition 0.000 description 3
- 235000008434 ginseng Nutrition 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000011031 large-scale manufacturing process Methods 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Studio Devices (AREA)
- Image Processing (AREA)
Abstract
This disclosure relates to the camera calibration method and apparatus based on gridiron pattern single image, wherein this method includes obtaining world coordinates step, obtains gridiron pattern graph card, and calculate the world coordinates of the angle point of gridiron pattern graph card；Image coordinate step is obtained, the chessboard table images of gridiron pattern graph card are obtained by camera, and obtains the image coordinate of angle point, wherein camera vertically shoots gridiron pattern graph card；It determines distortion factor step, obtains multiple angle points at least one straight line, wherein for each straight line by four angle points on gridiron pattern graph card, world coordinates and image coordinate based on multiple angle points obtain the distortion factor of camera；It determines intrinsic parameter step, based on two groups of parallel lines on gridiron pattern graph card, obtains the intrinsic parameter of camera, wherein two groups of parallel lines are mutually orthogonal；It determines outer parameter step, based on the image coordinate and world coordinates of the angle point on intrinsic parameter and chessboard table images, obtains the outer parameter of camera.By this method, the Fast Calibration of camera parameter is realized.
Description
Technical field
This disclosure relates to demarcate processing technology field, it is specifically related to a kind of twin-lens phase based on gridiron pattern single image
Machine scaling method, a kind of camera calibration method and apparatus based on gridiron pattern single image.
Background technique
The imaging process of camera is substantially the conversion process of coordinate system.It is the point in space first by world coordinate system turn
Camera coordinates system is changed to, is then projected into imaging plane again, image coordinate system is obtained, finally again by the figure on imaging plane
As coordinate system is transformed into pixel coordinate system.Conversion parameter process is to solve on camera calibration process nature.
Existing camera calibration is completed by scaling board mostly.The DLT standardization of early stage is by three-dimensional known to one
For the calibration object of absolute information come what is demarcated, to demarcating, object required precision is higher, not easy to manufacture in practical operation.For
Tsai standardization, realization, which is to rely on, carries out precise motion control to calibration object, and the method increase the complexity of calibration process
Degree.For Zhang standardization, then needs repeatedly to shoot a two-dimensional calibrations plate, corresponding staking-out work could be completed.
Therefore, on the basis of guaranteeing algorithm robustness, during the large-scale production of factory, a kind of easier calibration is needed
Method, to realize Fast Calibration.
Summary of the invention
In order to overcome problems of the prior art, the disclosure provides a kind of camera mark based on gridiron pattern single image
Determine method and apparatus.
In a first aspect, the embodiment of the present disclosure provides a kind of camera calibration method based on gridiron pattern single image comprising:
World coordinates step is obtained, obtains gridiron pattern graph card, and calculate the world coordinates of the angle point of gridiron pattern graph card；Obtain image coordinate
Step, the chessboard table images of gridiron pattern graph card are obtained by camera, and obtain the image coordinate of angle point, wherein camera is vertically clapped
Take the photograph gridiron pattern graph card；It determines distortion factor step, obtains multiple angle points at least one straight line, wherein each straight line warp
Four angle points on gridiron pattern graph card are crossed, world coordinates and image coordinate based on multiple angle points obtain the distortion factor of camera；
It determines intrinsic parameter step, based on two groups of parallel lines on gridiron pattern graph card, obtains the intrinsic parameter of camera, wherein two groups of parallel lines
It is mutually orthogonal；It determines outer parameter step, based on the image coordinate and world coordinates of the angle point on intrinsic parameter and chessboard table images, obtains
To the outer parameter of camera.
In one example, it determines that distortion factor step includes, obtains multiple angle points at least one straight line, wherein each
Straight line is by four angle points on gridiron pattern graph card；For four angle points of each line correspondences, by times of four angle points
Two angle points of anticipating combine, and constitute four line segments, based on the world coordinates and image coordinate of four angle points, obtain the generation of four line segments
Boundary's coordinate length and image coordinate length, and by the constant double ratio property of projection, obtain distortion factor.
In one example, determine that distortion factor step includes the multiple angle points obtained on a plurality of straight line, for a plurality of straight line pair
The multiple angle points answered respectively obtain multiple first distortion factors, and by the mean value of multiple first distortion factors, are as distortion
Number.
In one example, a plurality of straight line be located at gridiron pattern graph card top in the horizontal direction, in the horizontal direction in
Portion, lower part in the horizontal direction, left part along the vertical direction, middle part along the vertical direction, right part along the vertical direction, Yi Jiyan
Direction where two diagonal lines.
In one example, determine that intrinsic parameter step includes, based on two groups of parallel lines on gridiron pattern graph card, in chessboard table images
It is upper to obtain corresponding with two groups of parallel lines two end points and obtain intrinsic parameter using the image coordinate of two end points.
In one example, it determines that intrinsic parameter step includes, is based on distortion factor, the image of the angle point on chessboard table images is sat
Mark is corrected, and obtains the correction image coordinate of angle point；Based on two groups of parallel lines on gridiron pattern graph card, on chessboard table images
It obtains two end points corresponding with two groups of parallel lines and obtains intrinsic parameter using the correction image coordinate of two end points.
In one example, determine that outer parameter step includes, the image based on the angle point on intrinsic parameter, with chessboard table images is sat
Mark obtains the camera coordinates of angle point, and passes through the camera coordinates and world coordinates of angle point, obtains outer parameter.
In one example, it determines that outer parameter step includes, and is based on distortion factor, the image of the angle point on chessboard table images is sat
Mark is corrected, and obtains the correction image coordinate of angle point；Correction image based on the angle point on intrinsic parameter, with chessboard table images is sat
Mark obtains the camera coordinates of angle point, and passes through the camera coordinates and world coordinates of angle point, obtains outer parameter.
In one example, it determines that outer parameter step includes, and is based on distortion factor, the image of the angle point on chessboard table images is sat
Mark is corrected, and obtains the correction image coordinate of angle point；Correction image based on the angle point on intrinsic parameter, with chessboard table images is sat
Mark obtains the camera coordinates of angle point, and passes through the camera coordinates and world coordinates of angle point, obtains initial outer parameter；Pass through calculating
Back projection's residual error of angle point on chessboard table images, parameter is the analytical function of unknown number other than obtaining, and based on initial outer ginseng
Number, by nonlinear least square method, analytical function is calculated, obtains outer parameter.
In one example, the camera calibration method based on gridiron pattern single image further includes being arranged one on chessboard table images
Fixed point, the serial number based on fixed point determine the serial number of the angle point on chessboard table images, and according to angle point on chessboard table images
Serial number, determine serial number of the angle point on gridiron pattern graph card.
In one example, the camera calibration method based on gridiron pattern single image further includes being arranged one on chessboard table images
Mark point, wherein mark point is based on the positional relationship with fixed point, for demarcating the direction of chessboard table images.
In one example, the camera calibration method based on gridiron pattern single image further includes parameter optimisation step, passes through calculating
Back projection's residual error of angle point on gridiron pattern graph card is obtained using intrinsic parameter, outer parameter and distortion factor as the parsing letter of unknown number
Number, and by nonlinear least square method, analytical function is calculated, intrinsic parameter, outer parameter and the distortion system optimized
Number.
In one example, nonlinear least square method includes Lederberg-Marquardt algorithm.
Second aspect, the embodiment of the present disclosure provide a kind of twin-lens camera calibration method based on gridiron pattern single image,
Wherein, this method comprises: twin-lens camera includes left camera lens and right camera lens；The outer parameter of twin-lens camera includes rotation parameter R
With translation parameters T；By the above-mentioned camera calibration method based on gridiron pattern single image, the rotation parameter R of left camera lens is obtainedIt is left
With translation parameters TIt is leftAnd the rotation parameter R of right camera lensIt is rightWith translation parameters TIt is right, and it is based on rotation parameter RIt is leftWith translation parameters TIt is left,
And rotation parameter RIt is rightWith translation parameters TIt is right, obtain the rotation parameter R and translation parameters T of twin-lens camera.
The third aspect, the embodiment of the present disclosure provide a kind of camera calibration device based on gridiron pattern single image, the device
Have the function of realizing the camera calibration method based on gridiron pattern single image that above-mentioned first aspect is related to.The function can be with
By hardware realization, corresponding software realization can also be executed by hardware.The hardware or software include it is one or more with
The corresponding module of above-mentioned function.
In one example, a kind of camera calibration device based on gridiron pattern single image includes obtaining world coordinates module, is used
In acquisition gridiron pattern graph card, and calculate the world coordinates of the angle point of gridiron pattern graph card；Image coordinate module is obtained, for passing through phase
Machine obtains the chessboard table images of gridiron pattern graph card, and obtains the image coordinate of angle point, wherein camera vertically shoots chessboard trrellis diagram
Card；Distortion factor module is determined, for obtaining multiple angle points at least one straight line, wherein each straight line passes through chessboard
Four angle points on trrellis diagram card, world coordinates and image coordinate based on multiple angle points obtain the distortion factor of camera；In determination
Parameter module, for obtaining the intrinsic parameter of camera based on two groups of parallel lines on gridiron pattern graph card, wherein two groups of parallel lines phases
It is mutually orthogonal；Determine outer parameter module, for image coordinate and world coordinates based on intrinsic parameter with the angle point on chessboard table images,
Obtain the outer parameter of camera.
Fourth aspect, the embodiment of the present disclosure provide a kind of electronic equipment, wherein electronic equipment includes: memory, for depositing
Storage instruction；And processor, instruction execution first aspect for calling memory to store based on gridiron pattern single image
The twin-lens camera calibration method based on gridiron pattern single image of camera calibration method or second aspect.
5th aspect, the embodiment of the present disclosure provide a kind of computer readable storage medium, wherein computer-readable storage medium
Matter is stored with computer executable instructions, computer executable instructions when executed by the processor, execute first aspect based on
The camera calibration method of gridiron pattern single image or the twin-lens camera calibration side based on gridiron pattern single image of second aspect
Method.
The disclosure provides a kind of camera calibration method and apparatus based on gridiron pattern single image, wherein is based on gridiron pattern
The camera calibration method of single image is by choosing the angle point being located in a straight line, according to projective transformation Cross ration invariability, meter
The distortion factor for calculating camera, is then based on end point, by absolute conic equation, calculates the intrinsic parameter of camera, and calculate
The outer parameter of camera out, to complete the calibration to camera parameter.It, can be in the base for guaranteeing calibration result robustness by this method
On plinth, based on one width chessboard table images of shooting, the Fast Calibration of Lai Shixian camera parameter.
Detailed description of the invention
The following detailed description is read with reference to the accompanying drawings, above-mentioned and other purposes, the feature of disclosure embodiment
It will become prone to understand with advantage.In the accompanying drawings, embodiment of the present disclosure is shown by way of example rather than limitation,
Wherein:
Fig. 1 shows a kind of camera calibration method signal based on gridiron pattern single image of embodiment of the present disclosure offer
Figure；
Fig. 2 shows the chessboard table images schematic diagrames that a kind of camera that the embodiment of the present disclosure provides is shot；
Fig. 3 shows a kind of world coordinate system schematic diagram established based on gridiron pattern graph card of embodiment of the present disclosure offer；
Fig. 4 shows another camera calibration method signal based on gridiron pattern single image of embodiment of the present disclosure offer
Figure；
Fig. 5 shows a kind of camera calibration device signal based on gridiron pattern single image of embodiment of the present disclosure offer
Figure；
Fig. 6 shows a kind of electronic equipment schematic diagram of embodiment of the present disclosure offer.
Specific embodiment
The principle and spirit of the disclosure are described below with reference to several illustrative embodiments.It should be appreciated that providing this
A little embodiments are used for the purpose of making those skilled in the art can better understand that realizing the disclosure in turn, and be not with any
Mode limits the scope of the present disclosure.
Although being noted that the statements such as " first " used herein, " second " to describe implementation of the disclosure mode not
Same module, step and data etc., still the statement such as " first ", " second " is merely in different modules, step and data etc.
Between distinguish, and be not offered as specific sequence or significance level.In fact, the statements such as " first ", " second " are complete
It may be used interchangeably.
Fig. 1 is a kind of schematic diagram for camera calibration method based on gridiron pattern single image that the embodiment of the present disclosure provides.
As shown in Figure 1, the camera calibration method 100 based on gridiron pattern single image includes obtaining world coordinates step S101, figure is obtained
As coordinate step S102, distortion factor step S103 is determined, determine intrinsic parameter step S104 and determine outer parameter step S105.
Since the imaging process of camera is substantially the conversion process of coordinate, i.e., it can be related to world coordinates, camera coordinates
Conversion between image coordinate.Wherein, world coordinates is a kind of coordinate that target object location is expressed by world coordinate system,
World coordinate system refers to the coordinate system by establishing three-dimensional world, to describe a kind of coordinate of object position in real world
System；Camera coordinates are a kind of coordinates that target object location is expressed by camera coordinates system, and camera coordinates system refers on camera
Coordinate system is established, a kind of coordinate system of the position of object is described from the angle of camera, it is as communication world coordinate system
With one ring of centre of image coordinate system；Image coordinate is a kind of coordinate that target object location is expressed by image coordinate system, figure
As coordinate system refers to the coordinate system established on imaging plane, for object during describing imaging from camera coordinates system to figure
As the projection transmission relationship of coordinate system.
As a kind of possible embodiment, in obtaining world coordinates step S101, an available gridiron pattern graph card,
Wherein, the size of gridiron pattern graph card can be decided according to the actual requirements.The angle point on gridiron pattern graph card is obtained, it can be with gridiron pattern
The graph card upper left corner is origin, is horizontally to the right x-axis, is straight down y-axis, and the direction perpendicular to graph card is z-axis, establishes world's seat
Mark system, and calculate the world coordinates X of all angle points on gridiron pattern graph card.
In obtaining image coordinate step S102, above-mentioned gridiron pattern graph card can be shot by camera.Its
In, it is desirable that camera is fixed on the front in gridiron pattern graph card center, so that camera with vertical angle or can make camera lens
The angle formed between direction and gridiron pattern graph card direction is less than certain angle, such as can be 3 degree, to chess
Disk trrellis diagram card is shot.Based on this, the numerical value of the world coordinates of the angle point of the gridiron pattern graph card in the Z-axis direction can be enabled to be
Zero, calibrated and calculated process is simplified with this.As shown in Fig. 2, further, at the same adjust between mobile phone and gridiron pattern graph card away from
From so that gridiron pattern graph card covers viewing field of camera, the grey box part in diagram is viewing field of camera.At the same time, chess is obtained
Angle point on disk table images, and determine the image coordinate of the angle point.It should be noted that angle point and chessboard on gridiron pattern graph card
Angle point on table images is one-to-one.
In determining distortion factor step S103, by obtaining multiple angle points at least one straight line, wherein each
For straight line by four angle points on gridiron pattern graph card, the world coordinates and image coordinate of multiple angle points based on acquisition obtain phase
The distortion factor of machine.Wherein, distortion factor includes coefficient of radial distortion k1 and tangential distortion coefficient k2.
In determining intrinsic parameter step S104, by two groups of parallel lines on gridiron pattern graph card, the intrinsic parameter of camera is obtained
K, wherein two groups of parallel lines are mutually perpendicular to.
In determining outer parameter step S105, it is based on the image of fixed intrinsic parameter K and the angle point on chessboard table images
Coordinate world coordinates corresponding with the angle point, obtains outer parameter using projection formula, wherein outer parameter include rotation parameter R and
Translation parameters T.
The disclosure provides a kind of camera calibration method and apparatus based on gridiron pattern single image, wherein is based on gridiron pattern
The camera calibration method of single image is by choosing the angle point being located in a straight line, according to projective transformation Cross ration invariability, meter
The distortion factor for calculating camera, is then based on end point, by absolute conic equation, calculates the intrinsic parameter of camera, and calculate
The outer parameter of camera out, to complete the calibration to camera parameter.It, can be in the base for guaranteeing calibration result robustness by this method
On plinth, based on one width chessboard table images of shooting, the Fast Calibration of Lai Shixian camera parameter.
As a kind of possible embodiment, distortion factor step S103 is determined it is furthermore appreciated that being, available position
In four angle points on straight line, such as A, B, C, D, it is based on this, can determine this four corresponding world coordinates of angle point, by
It is imaged as A ', B ', C ', D ' on chessboard table images in four angle points, correspondingly, the image coordinate of four angle points is also true therewith
It is fixed.Now any two angle point of four angle points is combined, to constitute four line segments, for example, AC, BD, BC, AD, correspondingly,
Four line segments on chessboard table images respectively correspond as A ' C ', B ' D ', B ' C ', A ' D '.World coordinates based on four angle points and
Image coordinate, so can determine AC, BD, BC, AD world coordinates and its corresponding world coordinates length and A ' C ', B ' D ',
The image coordinate and its corresponding image coordinate length of B ' C ', A ' D '.
Due to the point in space on straight line, imaging will meet the constant double ratio principle of projection, therefore, four on the image
The line segment that angle point is constituted meets (AC*BD)/(BC*AD)=(A ' C ' * B ' D ')/(B ' C ' * A ' D ').
Because there is distortion in the image that camera obtains in shooting process, the image coordinate and reason of angle point on image
Think to meet distortion parameter model between image coordinate, i.e.,In formulaWherein, on image
The image coordinate of angle point is that the ideal image coordinate of (x, the y) angle point is (xd,yd)。
It should be noted that imaging will meet the constant double ratio of projection on the image due to the point in space on straight line
Principle, therefore, the line segment that four angle points are constituted meet (AC*BD)/(BC*AD)=(A ' C ' * B ' D ')/(B ' C ' * A ' D '), are
Refer to: the corresponding world coordinates length of world coordinates for the line segment that four angle points are constituted constitutes the ideograph of line segment with four angle points
As the corresponding ideal image coordinate length of coordinate, meet (AC*BD)/(BC*AD)=(A ' C ' * B ' D ')/(B ' C ' * A ' D ').Into
And in practical applications, can according to the corresponding world coordinates length of world coordinates and A ' C ' of AC, BD, BC, AD, B ' D ',
B ' C ', the corresponding image coordinate length of image coordinate of A ' D ' and distortion parameter model, calculate and obtain coefficient of radial distortion
K1 and tangential distortion coefficient k2.
As alternatively possible embodiment, determine distortion factor step S103 include obtain it is multiple on a plurality of straight line
Angle point, it should be noted that each straight line passes through corresponding four angle points on gridiron pattern graph card, in operating process
In, the world coordinates and image coordinate of multiple angle points based on a plurality of line correspondences utilize the constant double ratio of projection described above
Principle respectively obtains multiple first distortion factors, and makes even to the first distortion factor acquired according to the angle point on a plurality of straight line
Mean value, using the average value of multiple first distortion factors as distortion factor.Distortion system is acquired based on the angle point on a plurality of straight line
Number allows distortion factor more accurate.
Further, in order to enable the distortion factor arrived is more accurate, above-mentioned straight line can be located at gridiron pattern graph card
Top in the horizontal direction, middle part in the horizontal direction, lower part in the horizontal direction, left part along the vertical direction, along vertical
The middle part in direction, right part along the vertical direction, and along the direction where two diagonal lines.Due to being used to calculate distortion factor
Position where straight line is uniformly laid on gridiron pattern graph card, thus the distortion factor acquired can be made more accurate.
As a kind of possible embodiment, determine that intrinsic parameter step S104 may include, since one group of parallel lines is in image
Upper imaging can intersect at an end point, therefore, based on two groups of orthogonal parallel lines on gridiron pattern graph card, in gridiron pattern
Two end points v1, v2 corresponding with two groups of parallel lines are obtained on image, and obtain the image coordinate of two end points.Due to
Two groups of parallel lines are perpendicular to one another, therefore the image coordinate of the two end points meets constraintWherein K is internal reference
Number, by calculating, available intrinsic parameter K.
Further, in order to keep the intrinsic parameter K acquired more accurate, therefore, it is orthogonal parallel that multiple groups can be chosen
Line determines multiple end points based on the multiple groups parallel lines, and combines constraint equationIt obtains multiple about internal reference
The equivalent system of number K, obtains more accurate intrinsic parameter K using least square method.
It as alternatively possible embodiment, determines that intrinsic parameter step S104 may include, distortion factor is based on, to chessboard
The image coordinate of angle point on table images is corrected, to obtain the correction image coordinate of the angle point.Based on gridiron pattern graph card
Two groups of parallel lines perpendicular to one another, corresponding with two groups of parallel lines two end points v1, v2 are obtained on chessboard table images.
At this point, using the correction image coordinate of two end points, since the correction image coordinate of two end points meets constraintWherein K is intrinsic parameter, by calculating available intrinsic parameter K.Utilize the correction image coordinate meter of end point
Intrinsic parameter K is calculated, the intrinsic parameter K acquired can be made more accurate.
As a kind of possible embodiment, determine that outer parameter step S105 may include, and be based on intrinsic parameter, with chessboard trrellis diagram
As the image coordinate of upper angle point, inverse transformation is carried out to the angle point, to obtain the camera coordinates of the angle point, and passes through the angle point
Camera coordinates and world coordinates are based on projection formula, obtain outer parameter.The world coordinates for now enabling angle point is (x, y, 0), angle point
Camera coordinates be (x0,y0,-f), the image coordinate of angle point is (x1,y1), according to above-mentioned angle point inverse transformation it is found that meeting x0
=K-1*x1, corresponding y0=K-1*y1, according to projection formula it is found that meeting x0=R*x+T, correspondingly, y0=R*y+T；It is based on
This, can be calculated outer parameter, i.e. rotation parameter R and translation parameters T.
Further, in order to keep the outer parameter acquired more accurate, therefore, multiple angle points can be chosen and calculated, with
Multiple equivalent systems about outer parameter are obtained, and obtain more accurate outer parameter using least square method, is i.e. rotation ginseng
Number R and translation parameters T.
As another possible embodiment, determine that outer parameter step S105 includes: based on distortion factor, to chessboard trrellis diagram
As the image coordinate of upper angle point is corrected, to obtain the correction image coordinate of the angle point.Based on intrinsic parameter, with chessboard trrellis diagram
As the correction image coordinate of upper angle point, inverse transformation is carried out to the angle point, to obtain the camera coordinates of the angle point, and passes through the angle
The camera coordinates and world coordinates of point, are based on projection formula, obtain outer parameter.
As alternatively possible embodiment, determine that outer parameter step S105 includes: based on distortion factor, to chessboard trrellis diagram
As the image coordinate of upper angle point is corrected, to obtain the correction image coordinate of the angle point.Based on intrinsic parameter, with chessboard trrellis diagram
As the correction image coordinate of upper angle point, inverse transformation is carried out to the angle point, to obtain the camera coordinates of the angle point, and passes through the angle
The camera coordinates and world coordinates of point, are based on projection formula, obtain initial outer parameter.By calculating the angle point on chessboard table images
Back projection's residual error, parameter is the analytical function of unknown number other than obtaining, and based on obtained initial outer parameter, by non-linear
Analytical function is iterated calculating by least square method, to obtain outer parameter.
Based on back projection's residual error of angle point on obtained initial outer parameter and chessboard table images, pass through non-linear minimum two
The method of multiplication, which is iterated, calculates outer parameter, and the outer parameter made will be more accurate.
For example, enabling the correction image coordinate of the angle point on chessboard table images is U ', the world coordinates of the angle point is X, due to
The correction image coordinate of angle point is U ' and the world coordinates of the angle point be X is known, then, with back projection's residual error formulaFor error equation, available parameter, i.e. rotation parameter R and translation parameters T in addition
For the analytical function of unknown number, and the analytical function is calculated by nonlinear least square method, what is optimized is outer
Parameter.
It should be noted that nonlinear least square method can be Lederberg-Marquardt algorithm, it is also possible to
Other algorithms.
As a kind of possible embodiment, the camera calibration method 100 based on gridiron pattern single image further includes, in chessboard
It is arranged on table images with fixed point, the serial number based on the fixed point, to determine the serial number of other angle points on chessboard table images.By
Be in the angle point on the angle point and gridiron pattern graph card on chessboard table images it is one-to-one, therefore, can be according to angle point in chessboard
Serial number on table images determines serial number of the angle point on gridiron pattern graph card.When carrying out coordinate conversion, chessboard table images are prevented
On angle point and gridiron pattern graph card on angle point corresponding relationship occur mistake.
Further, a mark point can also be set on chessboard table images, which can be located at fixed point
Near, the other positions being also possible on chessboard table images are carrying out coordinate conversion with the direction for demarcating chessboard table images
During, for determining whether chessboard table images occur mirror face turning.
As shown in figure 3, in practical applications, can print a size 800mm*600mm, grid size is 25mm*
Three special grids are arranged in the gridiron pattern graph card of 25mm, the intermediate of the present gridiron pattern graph card, and two of them grid is connected, and enables
Angle point is fixed point among two grids, another isolated grid is mark point, it should be noted that in practical application
In, for the ease of distinguishing three special grids, the color of three special grids can be made to be different from other grids.Further
Ground can be horizontally to the right x-axis using the gridiron pattern graph card upper left corner as origin, be straight down y-axis, perpendicular to the direction of graph card
For z-axis, world coordinate system is established, and according to from left to right, is sorted from top to bottom, all angle points are ranked up, meanwhile, record
The serial number M of fixed point；All angle point U on chessboard table images are extracted using Harris Robust Algorithm of Image Corner Extraction, according to fixed point
Serial number M completes the sequence of all angle point U on chessboard table images, completes angle point in world coordinate system and image coordinate system with this
One-to-one correspondence.As alternatively possible embodiment, as shown in figure 4, the camera calibration method based on gridiron pattern single image
100 further include parameter optimisation step S106.Wherein, parameter optimisation step S106 is by calculating the anti-of the angle point on gridiron pattern graph card
Projection residual errors obtain using intrinsic parameter, outer parameter and distortion factor as the analytical function of unknown number, and pass through non-linear least square
Method calculates analytical function, intrinsic parameter, outer parameter and the distortion factor optimized.
For example, enabling the image coordinate of angle point on chessboard table images is U, the world coordinates of the angle point is X, correspondingly, with anti-
Projection residual errors formulaFor error equation, it is available with
Intrinsic parameter K, outer parameter, i.e. rotation parameter R and translation parameters T and distortion factor k1 and K2 are the analytical function of unknown number, and will
The analytical function is calculated by nonlinear least square method, intrinsic parameter, outer parameter and the distortion factor optimized.
Based on identical inventive concept, the embodiment of the present disclosure also provides a kind of twin-lens phase based on gridiron pattern single image
Machine scaling method, wherein this method includes that twin-lens camera includes left camera lens and right camera lens；Outer parameter include rotation parameter R and
Translation parameters T；By the above-mentioned camera calibration method based on gridiron pattern single image, the rotation parameter R of left camera lens is obtainedIt is leftWith
Translation parameters TIt is leftAnd the rotation parameter R of right camera lensIt is rightWith translation parameters TIt is right, and it is based on rotation parameter RIt is leftWith translation parameters TIt is left, with
And rotation parameter RIt is rightWith translation parameters TIt is right, pass through formulaWithObtain twin-lens camera
Rotation parameter R and translation parameters T.Correspondingly, this method can also pass through the above-mentioned camera based on gridiron pattern single image
Scaling method respectively obtains the distortion factor and intrinsic parameter of left camera lens and right camera lens.
Based on identical inventive concept, the embodiment of the present disclosure also provides a kind of camera calibration based on gridiron pattern single image
Device 200.The device as shown in Figure 5 includes obtaining world coordinates module 201, for obtaining gridiron pattern graph card, and calculating chessboard
The world coordinates of the angle point of trrellis diagram card；Image coordinate module 202 is obtained, for obtaining the gridiron pattern of gridiron pattern graph card by camera
Image, and obtain the image coordinate of angle point, wherein camera vertically shoots gridiron pattern graph card；It determines distortion factor module 203, uses
Multiple angle points at least one straight line of acquisition, wherein each straight line is based on by four angle points on gridiron pattern graph card
The world coordinates and image coordinate of multiple angle points, obtain the distortion factor of camera；Intrinsic parameter module 204 is determined, for being based on chess
Two groups of parallel lines on disk trrellis diagram card, obtain the intrinsic parameter of camera, wherein two groups of parallel lines are mutually orthogonal；Determine outer parameter mould
Block 205 obtains the outer ginseng of camera for image coordinate and world coordinates based on the angle point on intrinsic parameter and chessboard table images
Number.
In one example, it determines that distortion factor module 203 is used for, obtains multiple angle points at least one straight line, wherein is every
Straight line is by four angle points on gridiron pattern graph card, for four angle points of each line correspondences, by four angle points
The combination of any two angle point, constitutes four line segments, based on the world coordinates and image coordinate of four angle points, obtains four line segments
World coordinates length and image coordinate length, and by the constant double ratio property of projection, obtain distortion factor.
In one example, distortion factor module 203 is used in determining, multiple angle points on a plurality of straight line is obtained, for a plurality of
Multiple angle points of line correspondences respectively obtain multiple first distortion factors, and by the mean value of multiple first distortion factors, as abnormal
Variable coefficient.
In one example, a plurality of straight line be located at gridiron pattern graph card top in the horizontal direction, in the horizontal direction in
Portion, lower part in the horizontal direction, left part along the vertical direction, middle part along the vertical direction, right part along the vertical direction, Yi Jiyan
Direction where two diagonal lines.
In one example, determine that intrinsic parameter module 204 is used for, based on two groups of parallel lines on gridiron pattern graph card, in gridiron pattern
Two end points corresponding with two groups of parallel lines are obtained on image obtains intrinsic parameter using the image coordinate of two end points,
In, two groups of parallel lines are mutually orthogonal.
In one example, it determines that intrinsic parameter module 204 is used for, distortion factor is based on, to the figure of the angle point on chessboard table images
As coordinate is corrected, the correction image coordinate of angle point is obtained；Based on two groups of parallel lines on gridiron pattern graph card, in chessboard trrellis diagram
It obtains corresponding with two groups of parallel lines two end points as upper and obtains intrinsic parameter using the correction image coordinate of two end points,
Wherein, two groups of parallel lines are mutually orthogonal.
In one example, determine that outer parameter module 205 is used for, the image based on the angle point on intrinsic parameter, with chessboard table images
Coordinate obtains the camera coordinates of angle point, and passes through the camera coordinates and world coordinates of angle point, obtains outer parameter.
In one example, it determines that outer parameter module 205 is used for, distortion factor is based on, to the figure of the angle point on chessboard table images
As coordinate is corrected, the correction image coordinate of angle point is obtained；Correction chart based on the angle point on intrinsic parameter, with chessboard table images
As coordinate, the camera coordinates of angle point are obtained, and pass through the camera coordinates and world coordinates of angle point, obtain outer parameter.
In one example, it determines that outer parameter module 205 is used for, distortion factor is based on, to the figure of the angle point on chessboard table images
As coordinate is corrected, the correction image coordinate of angle point is obtained；Correction chart based on the angle point on intrinsic parameter, with chessboard table images
As coordinate, the camera coordinates of angle point are obtained, and pass through the camera coordinates and world coordinates of angle point, obtain initial outer parameter；Pass through
The back projection's residual error for calculating the angle point on chessboard table images, parameter is the analytical function of unknown number other than obtaining, and based on initial
Outer parameter is calculated analytical function by nonlinear least square method, obtains outer parameter.
In one example, the camera calibration device 200 based on gridiron pattern single image is also used to, and is arranged on chessboard table images
One fixed point, the serial number based on fixed point determine the serial number of the angle point on chessboard table images, and according to angle point in chessboard table images
On serial number, determine serial number of the angle point on gridiron pattern graph card.
In one example, the camera calibration device 200 based on gridiron pattern single image is also used to, and is arranged on chessboard table images
One mark point, wherein mark point is based on the positional relationship with fixed point, for demarcating the direction of chessboard table images.
In one example, the camera calibration device 200 based on gridiron pattern single image further includes parameter optimization module, for leading to
The back projection's residual error for calculating the angle point on gridiron pattern graph card is crossed, is obtained using intrinsic parameter, outer parameter and distortion factor as unknown number
Analytical function, and by nonlinear least square method, analytical function is calculated, the intrinsic parameter that is optimized, outer parameter and
Distortion factor.
In one example, nonlinear least square method includes Lederberg-Marquardt algorithm.
Fig. 6 shows a kind of electronic equipment 30 that an embodiment of the disclosure provides.As shown in fig. 6, the disclosure
The a kind of electronic equipment 30 that one embodiment provides, wherein the electronic equipment 30 includes memory 310, processor 320, defeated
Enter/export (Input/Output, I/O) interface 330.Wherein, memory 310, for storing instruction.Processor 320, for adjusting
Camera calibration method of the instruction execution disclosure based on gridiron pattern single image that is stored with memory 310 is based on gridiron pattern list
The twin-lens camera calibration method of width image.Wherein, processor 320 is connect with memory 310, I/O interface 330 respectively, such as
It can be attached by bindiny mechanism's (not shown) of bus system and/or other forms.Memory 310 can be used for storing program
And data, including the camera calibration based on gridiron pattern single image involved in the embodiment of the present disclosure or it is based on gridiron pattern single width figure
The program of the twin-lens camera calibration of picture, processor 320 are set by the program that operation is stored in memory 310 thereby executing electronics
Standby 30 various function application and data processing.
Processor 320 can use digital signal processor (Digital Signal in the embodiment of the present disclosure
Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), programmable patrol
At least one of volume array (Programmable Logic Array, PLA) example, in hardware realizes, the processor 320
It can be central processing unit (Central Processing Unit, CPU) or there is data-handling capacity and/or instruction
The combination of one or more of the processing unit of other forms of executive capability.
Memory 310 in the embodiment of the present disclosure may include one or more computer program products, the computer
Program product may include various forms of computer readable storage mediums, such as volatile memory and/or non-volatile deposit
Reservoir.The volatile memory for example may include random access memory (Random Access Memory, RAM) and/
Or cache memory (cache) etc..The nonvolatile memory for example may include read-only memory (Read-Only
Memory, ROM), flash memory (Flash Memory), hard disk (Hard Disk Drive, HDD) or solid state hard disk
(Solid-State Drive, SSD) etc..
In the embodiment of the present disclosure, I/O interface 330 can be used for receiving input instruction (such as number or character information, and
Generate key signals input related with the user setting of electronic equipment 30 and function control etc.), it can also be output to the outside various
Information (for example, image or sound etc.).In the embodiment of the present disclosure I/O interface 330 may include physical keyboard, function button (such as
Volume control button, switch key etc.), mouse, operating stick, trace ball, microphone, one in loudspeaker and touch panel etc.
It is a or multiple.
In some embodiments, present disclose provides a kind of computer readable storage medium, the computer-readable storages
Media storage has computer executable instructions, and computer executable instructions when executed by the processor, execute described above appoint
Where method.
Although description operation in a particular order in the accompanying drawings should not be construed as requiring specific shown in
Sequence or serial order operate to execute these operations, or shown in requirement execution whole to obtain desired result.In
In specific environment, multitask and parallel processing be may be advantageous.
Disclosed method and device can be completed using standard programming technology, using rule-based logic or its
His logic realizes various method and steps.It should also be noted that herein and the terms used in the claims " device "
" module " is intended to include using the realization of a line or multirow software code and/or hardware realization and/or for receiving input
Equipment.
One or more combined individually or with other equipment can be used in any step, operation or program described herein
A hardware or software module are executed or are realized.In one embodiment, software module use includes comprising computer program
The computer program product of the computer-readable medium of code is realized, can be executed by computer processor any for executing
Or whole described step, operation or programs.
For the purpose of example and description, the preceding description of disclosure implementation is had been presented for.Preceding description is not poor
The disclosure is restricted to exact form disclosed by also not the really wanting of act property, according to the above instruction there is likely to be various modifications and
Modification, or various changes and modifications may be obtained from the practice of the disclosure.Select and describe these embodiments and be in order to
Illustrate the principle and its practical application of the disclosure, so that those skilled in the art can be to be suitable for the special-purpose conceived
Come in a variety of embodiments with various modifications and using the disclosure.
Claims (17)
1. a kind of camera calibration method based on gridiron pattern single image, wherein described method includes following steps:
World coordinates step is obtained, obtains gridiron pattern graph card, and calculate the world coordinates of the angle point of the gridiron pattern graph card；
Image coordinate step is obtained, the chessboard table images of the gridiron pattern graph card are obtained by camera, and obtain the angle point
Image coordinate, wherein the camera vertically shoots the gridiron pattern graph card；
It determines distortion factor step, obtains multiple angle points at least one straight line, wherein straight line described in each passes through
Four angle points on the gridiron pattern graph card are obtained based on the world coordinates and image coordinate of the multiple angle point
The distortion factor of the camera；
It determines intrinsic parameter step, based on two groups of parallel lines on the gridiron pattern graph card, obtains the intrinsic parameter of the camera,
In, two groups of parallel lines are mutually orthogonal；
Determine outer parameter step, image coordinate and the world based on the angle point on the intrinsic parameter and the chessboard table images
Coordinate obtains the outer parameter of the camera.
2. according to the method described in claim 1, wherein, the determining distortion factor step includes:
Obtain multiple angle points at least one straight line, wherein straight line described in each is by the gridiron pattern graph card
Four angle points；
For four angle points of line correspondences described in each, by any two of four angle points
The angle point combination, constitutes four line segments, based on the world coordinates and image coordinate of four angle points, obtains described four
The world coordinates length and image coordinate length of line segment, and by the constant double ratio property of projection, obtain the distortion factor.
3. according to the method described in claim 2, wherein, the determining distortion factor step includes:
Multiple angle points on a plurality of straight line are obtained, for multiple angle points of a plurality of line correspondences, are respectively obtained
Multiple first distortion factors, and by the mean value of multiple first distortion factors, as the distortion factor.
4. according to the method described in claim 3, wherein,
The a plurality of straight line is located at the top in the horizontal direction of the gridiron pattern graph card, middle part in the horizontal direction, edge
The lower part of horizontal direction, left part along the vertical direction, middle part along the vertical direction, right part along the vertical direction, and along two
Direction where diagonal line.
5. according to the method described in claim 1, wherein, the determining intrinsic parameter step includes:
Based on two groups of parallel lines on the gridiron pattern graph card, obtained on the chessboard table images parallel with described two groups
Corresponding two end points of line obtain the intrinsic parameter using the image coordinate of described two end points.
6. according to the method described in claim 1, wherein, the determining intrinsic parameter step includes:
Based on the distortion factor, the image coordinate of the angle point on the chessboard table images is corrected, is obtained described
The correction image coordinate of angle point；
Based on two groups of parallel lines on the gridiron pattern graph card, obtained on the chessboard table images parallel with described two groups
Corresponding two end points of line obtain the intrinsic parameter using the correction image coordinate of described two end points.
7. according to the method described in claim 1, wherein, the outer parameter step of the determination includes:
Based on the image coordinate of the angle point on the intrinsic parameter, with the chessboard table images, the camera of the angle point is obtained
Coordinate, and by the camera coordinates of the angle point and the world coordinates, obtain the outer parameter.
8. according to the method described in claim 6, wherein, the outer parameter step of the determination includes:
Based on the distortion factor, the image coordinate of the angle point on the chessboard table images is corrected, is obtained described
The correction image coordinate of angle point；
The correction image coordinate based on the angle point on the intrinsic parameter, with the chessboard table images, obtains the angle
The camera coordinates of point, and by the camera coordinates of the angle point and the world coordinates, obtain the outer parameter.
9. according to the method described in claim 6, wherein, the outer parameter step of the determination includes:
Based on the distortion factor, the image coordinate of the angle point on the chessboard table images is corrected, is obtained described
The correction image coordinate of angle point；
The correction image coordinate based on the angle point on the intrinsic parameter, with the chessboard table images, obtains the angle
The camera coordinates of point, and by the camera coordinates of the angle point and the world coordinates, obtain initial outer parameter；
By calculating back projection's residual error of the angle point on the chessboard table images, parameter is the parsing of unknown number other than obtaining
Function, and calculated the analytical function by nonlinear least square method based on the initial outer parameter, obtain institute
State outer parameter.
10. according to the method described in claim 1, wherein, the method also includes:
A fixed point is set on the chessboard table images, based on the serial number of the fixed point, is determined on the chessboard table images
The angle point serial number, and the serial number according to the angle point on the chessboard table images determines the angle point in institute
State the serial number on gridiron pattern graph card.
11. according to the method described in claim 10, wherein, the method also includes:
A mark point is set on the chessboard table images, wherein the mark point based on the positional relationship with the fixed point,
For demarcating the direction of the chessboard table images.
12. according to the method described in claim 1, wherein, the method also includes:
Parameter optimisation step, by calculating back projection's residual error of the angle point on the gridiron pattern graph card, obtain with intrinsic parameter,
Outer parameter and distortion factor are the analytical function of unknown number, and by nonlinear least square method, the analytical function is carried out
It calculates, the intrinsic parameter, the outer parameter and the distortion factor optimized.
13. the method according to claim 9 or 12, wherein
The nonlinear least square method includes Lederberg-Marquardt algorithm.
14. a kind of twin-lens camera calibration method based on gridiron pattern single image, wherein the described method includes:
The twin-lens camera includes left camera lens and right camera lens；
The outer parameter of the twin-lens camera includes rotation parameter R and translation parameters T；
By the described in any item camera calibration methods based on gridiron pattern single image of such as claim 1-13, the left side is obtained
The rotation parameter R of camera lensIt is leftWith translation parameters TIt is leftAnd the rotation parameter R of the right camera lensIt is rightWith translation parameters TIt is right, and based on institute
State rotation parameter RIt is leftWith the translation parameters TIt is leftAnd the rotation parameter RIt is rightWith the translation parameters TIt is right, obtain the bimirror
The rotation parameter R and translation parameters T of head camera.
15. a kind of camera calibration device based on gridiron pattern single image, wherein described device includes:
World coordinates module is obtained, for obtaining gridiron pattern graph card, and calculates the world coordinates of the angle point of the gridiron pattern graph card；
Image coordinate module is obtained, for obtaining the chessboard table images of the gridiron pattern graph card by camera, and obtains the angle
The image coordinate of point, wherein the camera vertically shoots the gridiron pattern graph card；
Distortion factor module is determined, for obtaining multiple angle points at least one straight line, wherein straight line described in each
By four angle points on the gridiron pattern graph card, based on the world coordinates and image coordinate of the multiple angle point,
Obtain the distortion factor of the camera；
Determine intrinsic parameter module, for obtaining the intrinsic parameter of the camera based on two groups of parallel lines on the gridiron pattern graph card,
Wherein, two groups of parallel lines are mutually orthogonal；
Determine outer parameter module, for based on the intrinsic parameter and the angle point on the chessboard table images image coordinate and
World coordinates obtains the outer parameter of the camera.
16. a kind of electronic equipment, wherein the electronic equipment includes:
Memory, for storing instruction；And
Processor, based on gridiron pattern described in any one of instruction execution claim 1-13 for calling memory storage
Based on the twin-lens camera calibration side of gridiron pattern single image described in the camera calibration method or claim 14 of single image
Method.
17. a kind of computer readable storage medium, wherein
The computer-readable recording medium storage has computer executable instructions, and the computer executable instructions are by handling
When device executes, perform claim requires camera calibration method or right based on gridiron pattern single image described in any one of 1-13 to want
Twin-lens camera calibration method described in asking 14 based on gridiron pattern single image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910755404.4A CN110490940A (en) | 2019-08-15 | 2019-08-15 | Camera calibration method and apparatus based on gridiron pattern single image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910755404.4A CN110490940A (en) | 2019-08-15 | 2019-08-15 | Camera calibration method and apparatus based on gridiron pattern single image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110490940A true CN110490940A (en) | 2019-11-22 |
Family
ID=68549765
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910755404.4A Pending CN110490940A (en) | 2019-08-15 | 2019-08-15 | Camera calibration method and apparatus based on gridiron pattern single image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110490940A (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110930336A (en) * | 2019-11-29 | 2020-03-27 | 深圳市商汤科技有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN111047650A (en) * | 2019-12-02 | 2020-04-21 | 北京深测科技有限公司 | Parameter calibration method for time-of-flight camera |
| CN111179356A (en) * | 2019-12-25 | 2020-05-19 | 北京中科慧眼科技有限公司 | Binocular camera calibration method, device and system based on Aruco code and calibration board |
| CN111243033A (en) * | 2020-01-10 | 2020-06-05 | 大连理工大学 | Method for optimizing external parameters of binocular camera |
| CN111340893A (en) * | 2020-03-24 | 2020-06-26 | 深圳奥比中光科技有限公司 | Calibration plate, calibration method and calibration system |
| CN112070846A (en) * | 2020-09-14 | 2020-12-11 | 北京华严互娱科技有限公司 | Real-time human body motion tracking method and system based on video |
| CN112184662A (en) * | 2020-09-27 | 2021-01-05 | 成都数之联科技有限公司 | Camera external parameter initial method and system applied to unmanned aerial vehicle image stitching |
| CN112233187A (en) * | 2020-10-20 | 2021-01-15 | 深圳无境智能机器人有限公司 | Convenient and stable rgbd camera external parameter calibration method |
| CN112465760A (en) * | 2020-11-19 | 2021-03-09 | 深圳惠牛科技有限公司 | Checkerboard corner point identification method, device, equipment and storage medium |
| CN112614193A (en) * | 2020-12-25 | 2021-04-06 | 中国农业大学 | Intelligent calibration method for wheat green turning period spray interested region based on machine vision |
| CN112726351A (en) * | 2020-12-30 | 2021-04-30 | 上海同陆云交通科技有限公司 | Vehicle-mounted portable lightweight intelligent inspection method and system |
| CN112862895A (en) * | 2019-11-27 | 2021-05-28 | 杭州海康威视数字技术股份有限公司 | Fisheye camera calibration method, device and system |
| CN112907677A (en) * | 2019-12-04 | 2021-06-04 | 杭州海康威视数字技术股份有限公司 | Camera calibration method and device for single-frame image and storage medium |
| CN113409396A (en) * | 2021-05-11 | 2021-09-17 | 广州敏视数码科技有限公司 | Calibration method of ADAS monocular camera |
| CN113436272A (en) * | 2021-05-21 | 2021-09-24 | 中国科学院自动化研究所 | Spherical refraction correction method for underwater stereoscopic vision system and electronic equipment |
| CN114596368A (en) * | 2022-05-10 | 2022-06-07 | 腾讯科技（深圳）有限公司 | Data processing method and device, computer equipment and readable storage medium |
| CN114902647A (en) * | 2020-01-20 | 2022-08-12 | 日立安斯泰莫株式会社 | Image correction device and image correction method |
| CN115457147A (en) * | 2022-09-16 | 2022-12-09 | 北京的卢深视科技有限公司 | Camera calibration method, electronic device and storage medium |
| CN116030450A (en) * | 2023-03-23 | 2023-04-28 | 摩尔线程智能科技(北京)有限责任公司 | Checkerboard corner recognition method, device, equipment and medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101231750A (en) * | 2008-02-21 | 2008-07-30 | 南京航空航天大学 | Calibrating method of binocular three-dimensional measuring system |
| CN102930544A (en) * | 2012-11-05 | 2013-02-13 | 北京理工大学 | Parameter calibration system of vehicle-mounted camera |
| CN103759670A (en) * | 2014-01-06 | 2014-04-30 | 四川虹微技术有限公司 | Object three-dimensional information acquisition method based on digital close range photography |
| CN104807405A (en) * | 2015-04-27 | 2015-07-29 | 四川大学 | Three-dimensional coordinate measurement method based on light ray angle calibration |
| CN105931222A (en) * | 2016-04-13 | 2016-09-07 | 成都信息工程大学 | High-precision camera calibration method via low-precision 2D planar target |
| CN106887023A (en) * | 2017-02-21 | 2017-06-23 | 成都通甲优博科技有限责任公司 | For scaling board and its scaling method and calibration system that binocular camera is demarcated |
| CN108053450A (en) * | 2018-01-22 | 2018-05-18 | 浙江大学 | A kind of high-precision binocular camera scaling method based on multiple constraint |
| CN108986172A (en) * | 2018-07-25 | 2018-12-11 | 西北工业大学 | A kind of single-view linear camera scaling method towards small depth of field system |
| CN109242918A (en) * | 2018-11-15 | 2019-01-18 | 中国直升机设计研究所 | A kind of helicopter-mounted binocular stereo vision scaling method |
| CN109978955A (en) * | 2019-03-11 | 2019-07-05 | 武汉环宇智行科技有限公司 | A kind of efficient mask method for combining laser point cloud and image |
-
2019
- 2019-08-15 CN CN201910755404.4A patent/CN110490940A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101231750A (en) * | 2008-02-21 | 2008-07-30 | 南京航空航天大学 | Calibrating method of binocular three-dimensional measuring system |
| CN102930544A (en) * | 2012-11-05 | 2013-02-13 | 北京理工大学 | Parameter calibration system of vehicle-mounted camera |
| CN103759670A (en) * | 2014-01-06 | 2014-04-30 | 四川虹微技术有限公司 | Object three-dimensional information acquisition method based on digital close range photography |
| CN104807405A (en) * | 2015-04-27 | 2015-07-29 | 四川大学 | Three-dimensional coordinate measurement method based on light ray angle calibration |
| CN105931222A (en) * | 2016-04-13 | 2016-09-07 | 成都信息工程大学 | High-precision camera calibration method via low-precision 2D planar target |
| CN106887023A (en) * | 2017-02-21 | 2017-06-23 | 成都通甲优博科技有限责任公司 | For scaling board and its scaling method and calibration system that binocular camera is demarcated |
| CN108053450A (en) * | 2018-01-22 | 2018-05-18 | 浙江大学 | A kind of high-precision binocular camera scaling method based on multiple constraint |
| CN108986172A (en) * | 2018-07-25 | 2018-12-11 | 西北工业大学 | A kind of single-view linear camera scaling method towards small depth of field system |
| CN109242918A (en) * | 2018-11-15 | 2019-01-18 | 中国直升机设计研究所 | A kind of helicopter-mounted binocular stereo vision scaling method |
| CN109978955A (en) * | 2019-03-11 | 2019-07-05 | 武汉环宇智行科技有限公司 | A kind of efficient mask method for combining laser point cloud and image |
Non-Patent Citations (2)
| Title |
|---|
| 李竹良等: "基于单幅图片的相机完全标定", 《计算机工程》 * |
| 马峰: "基于二维图像的三维建模技术的研究", 《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》 * |
Cited By (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112862895B (en) * | 2019-11-27 | 2023-10-10 | 杭州海康威视数字技术股份有限公司 | Fisheye camera calibration method, device and system |
| CN112862895A (en) * | 2019-11-27 | 2021-05-28 | 杭州海康威视数字技术股份有限公司 | Fisheye camera calibration method, device and system |
| CN110930336B (en) * | 2019-11-29 | 2023-11-28 | 深圳市商汤科技有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN110930336A (en) * | 2019-11-29 | 2020-03-27 | 深圳市商汤科技有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN111047650A (en) * | 2019-12-02 | 2020-04-21 | 北京深测科技有限公司 | Parameter calibration method for time-of-flight camera |
| CN111047650B (en) * | 2019-12-02 | 2023-09-01 | 北京深测科技有限公司 | Parameter calibration method for time-of-flight camera |
| CN112907677A (en) * | 2019-12-04 | 2021-06-04 | 杭州海康威视数字技术股份有限公司 | Camera calibration method and device for single-frame image and storage medium |
| CN112907677B (en) * | 2019-12-04 | 2023-07-25 | 杭州海康威视数字技术股份有限公司 | Camera calibration method and device for single-frame image and storage medium |
| CN111179356A (en) * | 2019-12-25 | 2020-05-19 | 北京中科慧眼科技有限公司 | Binocular camera calibration method, device and system based on Aruco code and calibration board |
| CN111243033A (en) * | 2020-01-10 | 2020-06-05 | 大连理工大学 | Method for optimizing external parameters of binocular camera |
| CN111243033B (en) * | 2020-01-10 | 2022-09-20 | 大连理工大学 | Method for optimizing external parameters of binocular camera |
| CN114902647A (en) * | 2020-01-20 | 2022-08-12 | 日立安斯泰莫株式会社 | Image correction device and image correction method |
| CN111340893A (en) * | 2020-03-24 | 2020-06-26 | 深圳奥比中光科技有限公司 | Calibration plate, calibration method and calibration system |
| CN112070846A (en) * | 2020-09-14 | 2020-12-11 | 北京华严互娱科技有限公司 | Real-time human body motion tracking method and system based on video |
| CN112184662A (en) * | 2020-09-27 | 2021-01-05 | 成都数之联科技有限公司 | Camera external parameter initial method and system applied to unmanned aerial vehicle image stitching |
| CN112184662B (en) * | 2020-09-27 | 2023-12-15 | 成都数之联科技股份有限公司 | Camera external parameter initial method and system applied to unmanned aerial vehicle image stitching |
| CN112233187A (en) * | 2020-10-20 | 2021-01-15 | 深圳无境智能机器人有限公司 | Convenient and stable rgbd camera external parameter calibration method |
| CN112465760A (en) * | 2020-11-19 | 2021-03-09 | 深圳惠牛科技有限公司 | Checkerboard corner point identification method, device, equipment and storage medium |
| CN112614193B (en) * | 2020-12-25 | 2024-03-22 | 中国农业大学 | Intelligent calibration method for wheat green-turning stage spraying region of interest based on machine vision |
| CN112614193A (en) * | 2020-12-25 | 2021-04-06 | 中国农业大学 | Intelligent calibration method for wheat green turning period spray interested region based on machine vision |
| CN112726351B (en) * | 2020-12-30 | 2021-08-27 | 上海同陆云交通科技有限公司 | Vehicle-mounted portable lightweight intelligent inspection method and system |
| CN112726351A (en) * | 2020-12-30 | 2021-04-30 | 上海同陆云交通科技有限公司 | Vehicle-mounted portable lightweight intelligent inspection method and system |
| CN113409396A (en) * | 2021-05-11 | 2021-09-17 | 广州敏视数码科技有限公司 | Calibration method of ADAS monocular camera |
| CN113409396B (en) * | 2021-05-11 | 2024-03-29 | 广州敏视数码科技有限公司 | Calibrating method of ADAS monocular camera |
| CN113436272A (en) * | 2021-05-21 | 2021-09-24 | 中国科学院自动化研究所 | Spherical refraction correction method for underwater stereoscopic vision system and electronic equipment |
| CN114596368B (en) * | 2022-05-10 | 2022-07-08 | 腾讯科技（深圳）有限公司 | Data processing method and device, computer equipment and readable storage medium |
| CN114596368A (en) * | 2022-05-10 | 2022-06-07 | 腾讯科技（深圳）有限公司 | Data processing method and device, computer equipment and readable storage medium |
| CN115457147A (en) * | 2022-09-16 | 2022-12-09 | 北京的卢深视科技有限公司 | Camera calibration method, electronic device and storage medium |
| CN116030450A (en) * | 2023-03-23 | 2023-04-28 | 摩尔线程智能科技(北京)有限责任公司 | Checkerboard corner recognition method, device, equipment and medium |
| CN116030450B (en) * | 2023-03-23 | 2023-12-19 | 摩尔线程智能科技(北京)有限责任公司 | Checkerboard corner recognition method, device, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110490940A (en) | Camera calibration method and apparatus based on gridiron pattern single image | |
| CN106447727B (en) | Method of estimating parameter of 3D display device and 3D display device using the same | |
| US8571350B2 (en) | Image processing system with image alignment mechanism and method of operation thereof | |
| CN111738923A (en) | Image processing method, apparatus and storage medium | |
| JP2021120678A (en) | Method and apparatus for calibrating external parameters of image acquisition device, device, storage medium and program | |
| CN104376572A (en) | Mobile terminal camera calibrating method | |
| US11524406B2 (en) | Calibration method and device for robotic arm system | |
| CN1982934A (en) | Image taking apparatus, image processing method, and image processing program | |
| CN113920205B (en) | Calibration method of non-coaxial camera | |
| CN107449374A (en) | The vision auxiliary laser galvanometer scanning system and its field calibration method of flexible layout | |
| CN112288826B (en) | Calibration method and device of binocular camera and terminal | |
| CN108769462A (en) | Free-viewing angle scene walkthrough method and device | |
| CN103843329A (en) | Methods and apparatus for conditional display of a stereoscopic image pair | |
| CN104089628A (en) | Self-adaption geometric calibration method of light field camera | |
| CN109341718B (en) | Calibration method and device based on multi-view vision | |
| CN105678736A (en) | Image processing system with aperture change depth estimation and method of operation thereof | |
| WO2017014933A1 (en) | Systems and methods for selecting an image transform | |
| EP3309750B1 (en) | Image processing apparatus and image processing method | |
| CN103533326A (en) | System and method for alignment of stereo views | |
| CN112396663B (en) | Visual calibration method, device, equipment and medium for multi-depth camera | |
| CN105847641A (en) | Imaging device, imaging method and electronic device | |
| WO2021106027A1 (en) | Camera parameter derivation device, camera parameter derivation method, and camera parameter derivation program | |
| CN106303208B (en) | Image Acquisition control method and device | |
| CN106375648B (en) | Image Acquisition control method and device | |
| Orekhov et al. | Universal camera calibration with automatic distortion model selection |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191122 |