CN110337674A - Three-dimensional rebuilding method, device, equipment and storage medium - Google Patents
Three-dimensional rebuilding method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN110337674A CN110337674A CN201980000842.8A CN201980000842A CN110337674A CN 110337674 A CN110337674 A CN 110337674A CN 201980000842 A CN201980000842 A CN 201980000842A CN 110337674 A CN110337674 A CN 110337674A
- Authority
- CN
- China
- Prior art keywords
- calibration
- structure light
- maps
- calibration maps
- measurement image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- 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 provides a kind of three-dimensional rebuilding method, device, equipment and storage medium, this method comprises: obtaining each corresponding first position coordinate of structure light figure on measurement image；According to measurement image, the first calibration maps and the second calibration maps, determine the calibration section of each structure light figure on measurement image, first calibration maps are the calibration figures demarcated on the first calibration face, second calibration maps are the calibration figures demarcated on the second calibration face, and the first calibration face, the second calibration face are parallel with camera plane；According to the calibration section of each structure light figure on measurement image, the depth value of each first position coordinate is calculated；According to the depth value of each first position coordinate and calibration reconstruction parameter, three-dimensional reconstruction is carried out to measurement image, improves the efficiency of three-dimensional reconstruction.
Description
Technical field
The present invention relates to technical field of computer vision more particularly to a kind of three-dimensional rebuilding method, device, equipment and storages
Medium.
Background technique
Three-dimensional reconstruction is an important research field of computer vision, refers to and establishes suitable computer table to three-dimension object
The mathematical model shown and handled, for restoring the distance between camera and object in object surface shape or restoration scenario, fastly
The three-dimensional configuration of quick-recovery scene and object improves the efficiency of measurement and modeling, is widely used in ancient building digitlization, historical relic number
The scenes such as word, robot localization navigation, reverse-engineering, three-dimensional reconstruction are also the void for establishing expression objective world in a computer
The key technology for intending reality, in terms of bio-identification, compared to traditional two dimensional model, threedimensional model has bigger difference empty
Between, the acquiring technology of three-dimensional information has the necessity of its development.
In the prior art, the method for three-dimensional reconstruction is roughly divided into Stereo Vision (binocular, three mesh and multi-vision visual), knot
Structure light method for reconstructing, structure from motion (Structure from Motion, SFM) etc..Wherein, structured light reconstruction method
Some superiority is above occupied in application, structured light reconstruction method actively projects known compile to object or scene using structured light projector
Controllable luminous point, striation or the smooth surface of code structure, and the image of the object or scene by camera acquisition with projection pattern, lead to
Computer vision technique processing image is crossed, coding pattern is parsed, obtains the three-dimensional information of object or scene, construct object or scene
Threedimensional model.The key of structured light reconstruction technology is system calibrating and Stereo matching.
However structured light reconstruction method in the prior art, it rebuilds the complicated and three-dimensional correction accuracy of process and requires height, cause
The efficiency of three-dimensional reconstruction is lower.
Summary of the invention
The present invention provides a kind of three-dimensional rebuilding method, device, equipment and storage medium, to realize to three-dimensional rebuilding method
Simplify, improves the efficiency of three-dimensional reconstruction.
In a first aspect, the embodiment of the present invention provides a kind of three-dimensional rebuilding method, comprising:
Obtain each corresponding first position coordinate of structure light figure on measurement image.
According to measurement image, the first calibration maps and the second calibration maps, the mark of each structure light figure on measurement image is determined
Determine section, the first calibration maps are the calibration figures demarcated on the first calibration face, and the second calibration maps are in the second calibration face
The calibration figure of upper calibration, the first calibration face, the second calibration face are parallel with camera plane.
According to the calibration section of each structure light figure on measurement image, the depth value of each first position coordinate is calculated.
According to the depth value of each first position coordinate and calibration reconstruction parameter, three-dimensional reconstruction is carried out to measurement image.
In the present solution, determining that upper each structure is schemed in measurement by according to measurement image, the first calibration maps and the second calibration maps
The calibration section of light figure calculates each first position then according to the calibration section of each structure light figure on measurement image
The depth value of coordinate carries out three to measurement image finally according to the depth value of each first position coordinate and calibration reconstruction parameter
Dimension is rebuild, and not only realizes the three-dimensional reconstruction to measurement image, but also directly pass through each structure light figure on measurement image
The step of demarcating section, calculate the depth value of each first position coordinate, avoiding three-dimensional correction, improves the effect of three-dimensional reconstruction
Rate.
Optionally, in the depth value and calibration reconstruction parameter according to each first position coordinate, three are carried out to measurement image
Before dimension is rebuild, further includes:
It obtains third calibration maps and the 4th calibration maps, third calibration maps is the non-structural cursor demarcated on the first calibration face
Fixed figure, the 4th calibration maps are the non-structural light calibration maps demarcated on the second calibration face；
According to third calibration maps, the 4th calibration maps and camera imaging model, calibration reconstruction parameter is determined.
In the present solution, realizing the calibration to depth value by the first calibration maps and the second calibration maps, then third is demarcated
Figure and the 4th calibration maps and camera imaging model determine calibration reconstruction parameter, realize depth value calibration and calibration reconstruction parameter
Separation, reduce the required precision of calibration, thereby reduce calibration difficulty.
Optionally, according to third calibration maps, the 4th calibration maps and camera imaging model, calibration reconstruction parameter, packet are determined
It includes:
In third calibration maps and the 4th calibration maps, multiple groups pixel coordinate and the corresponding calibration of multiple groups pixel coordinate are obtained
Coordinate on plate.
For multiple groups pixel coordinate, respectively by the seat on every group of pixel coordinate and the corresponding scaling board of every group of pixel coordinate
Mark inputs in camera imaging model, to determine the homography matrix of plane arbitrarily parallel with camera plane in pre-set space.
Correspondingly, being carried out to measurement image three-dimensional according to the depth value of each first position coordinate and calibration reconstruction parameter
It rebuilds, comprising:
It is answered according to the list of plane arbitrarily parallel with camera plane in the depth value of each first position coordinate, pre-set space
Matrix and camera imaging model carry out three-dimensional reconstruction to measurement image.
In the present solution, passing through third calibration maps and pixel coordinate and the corresponding calibration of pixel coordinate in the 4th calibration maps
Coordinate on plate determines the homography matrix of plane arbitrarily parallel with camera plane in pre-set space, realizes to pre-set space
The inside determination of the three-dimensional coordinate of plane arbitrarily parallel with camera plane, and then realize the three-dimensional reconstruction to measurement image.
Optionally, according to measurement image, the first calibration maps and the second calibration maps, each structure light figure on measurement image is determined
The calibration section of shape, comprising:
Structure light figure in matching measurement image, the first calibration maps and the second calibration maps.
Determine first position coordinate of each structure light figure in measurement image, the second position in the first calibration maps
Coordinate and the third place coordinate in the second calibration maps.
According to the first position coordinate, second position coordinate and the third place coordinate of each structure light figure, measurement is determined
The calibration section of each structure light figure on image.
Optionally, according to measurement image, the first calibration maps and the second calibration maps, each structure light figure on measurement image is determined
The calibration section of shape, comprising:
The structure light figure for matching the first calibration maps and the second calibration maps determines every in the first calibration maps and the second calibration maps
The coordinate correspondence relationship of a structure light figure.
The structure light figure of matching measurement image and the first calibration maps determines each structure light figure in measurement image
First position coordinate and the second position coordinate in the first calibration maps.
According to each structure light figure in first position coordinate, second position coordinate and the first calibration maps and the second calibration maps
The coordinate correspondence relationship of shape determines the calibration section of each structure light figure on measurement image.
In the present solution, by determining that the first calibration maps and the coordinate pair of structure light figure each in the second calibration maps should close
System, realizes the compression to nominal data, has saved a large amount of memory space.
Optionally, according to the calibration section of each structure light figure of measurement image, each first position coordinate is calculated
Depth value, comprising:
Determine each structure light figure in the first parallax of measurement image and the first calibration maps.
In the calibration section of each structure light figure, determine that section in addition to the first parallax is the second parallax, second
Parallax is parallax of the structure light figure in measurement image and the second calibration maps.
According to the first parallax and the second parallax, the depth value of each first position coordinate is calculated.
Device, equipment, storage medium and computer program product provided by the embodiments of the present application, content is described below
It can refer to the three-dimensional rebuilding method that first aspect and first aspect optional way provide with effect, repeat no more.
Second aspect, the embodiment of the present application provide a kind of three-dimensional reconstruction apparatus, comprising:
First obtains module, for obtaining each corresponding first position coordinate of structure light figure on measurement image.
First determining module, for determining every on measurement image according to measurement image, the first calibration maps and the second calibration maps
The calibration section of a structure light figure, the first calibration maps are the calibration figure demarcated on the first calibration face, the second calibration
Figure is the calibration figure demarcated on the second calibration face, and the first calibration face, the second calibration face are parallel with camera plane.
Second determining module calculates each first for the calibration section according to each structure light figure on measurement image
The depth value of position coordinates.
Rebuild module, for according to the depth value of each first position coordinate and calibration reconstruction parameter, to measurement image into
Row three-dimensional reconstruction.
Optionally, three-dimensional reconstruction apparatus provided by the embodiments of the present application, further includes:
Second obtains module, and for obtaining third calibration maps and the 4th calibration maps, third calibration maps are in the first calibration face
The non-structural light calibration maps of upper calibration, the 4th calibration maps are the non-structural light calibration maps demarcated on the second calibration face.
Third determining module, for determining calibration weight according to third calibration maps, the 4th calibration maps and camera imaging model
Build parameter.
Optionally, third determining module is specifically used for:
In third calibration maps and the 4th calibration maps, multiple groups pixel coordinate and the corresponding calibration of multiple groups pixel coordinate are obtained
Coordinate on plate.
For multiple groups pixel coordinate, respectively by the seat on every group of pixel coordinate and the corresponding scaling board of every group of pixel coordinate
Mark inputs in camera imaging model, to determine the homography matrix of plane arbitrarily parallel with camera plane in pre-set space.
It is specifically used for correspondingly, rebuilding module:
It is answered according to the list of plane arbitrarily parallel with camera plane in the depth value of each first position coordinate, pre-set space
Matrix and camera imaging model carry out three-dimensional reconstruction to measurement image.
Optionally, the first determining module is specifically used for:
Structure light figure in matching measurement image, the first calibration maps and the second calibration maps.
Determine first position coordinate of each structure light figure in measurement image, the second position in the first calibration maps
Coordinate and the third place coordinate in the second calibration maps.
According to the first position coordinate, second position coordinate and the third place coordinate of each structure light figure, measurement is determined
The calibration section of each structure light figure on image.
Optionally, the first determining module is specifically used for:
The structure light figure for matching the first calibration maps and the second calibration maps determines every in the first calibration maps and the second calibration maps
The coordinate correspondence relationship of a structure light figure.
The structure light figure of matching measurement image and the first calibration maps determines each structure light figure in measurement image
First position coordinate and the second position coordinate in the first calibration maps.
According to each structure light figure in first position coordinate, second position coordinate and the first calibration maps and the second calibration maps
The coordinate correspondence relationship of shape determines the calibration section of each structure light figure on measurement image.
Optionally, the second determining module is specifically used for:
Determine each structure light figure in the first parallax of measurement image and the first calibration maps.
In the calibration section of each structure light figure, determine that section in addition to the first parallax is the second parallax, second
Parallax is parallax of the structure light figure in measurement image and the second calibration maps.
According to the first parallax and the second parallax, the depth value of each first position coordinate is calculated.
The third aspect, the embodiment of the present application provide a kind of equipment, comprising:
Processor；Memory；And computer program；Wherein, computer program is stored in memory, and is matched
It is set to and is executed by processor, computer program includes for executing the three-dimensional reconstruction such as first aspect and first aspect optional way
Method.
Fourth aspect, the embodiment of the present application provide a kind of computer readable storage medium, and computer readable storage medium is deposited
Contain computer program, optional way provides in terms of computer program executes server such as first aspect and first party three
Tie up method for reconstructing.
5th aspect, the embodiment of the present invention provide a kind of computer program product, comprising: executable instruction can be performed and refer to
Enable the three-dimensional rebuilding method for realizing such as first aspect or first aspect optional way.
Three-dimensional rebuilding method, device, equipment and storage medium provided by the invention, by obtaining each knot on measurement image
The corresponding first position coordinate of structure light figure is determined and is surveyed then according to measurement image, the first calibration maps and the second calibration maps
The calibration section of each structure light figure on spirogram picture, the first calibration maps are the calibrations demarcated on the first calibration face
Figure, the second calibration maps are the calibration figures demarcated on the second calibration face, and the first calibration face, the second calibration face and camera are flat
Face is parallel, according to the calibration section of each structure light figure on measurement image, calculates the depth value of each first position coordinate, most
Afterwards according to the depth value of each first position coordinate and calibration reconstruction parameter, three-dimensional reconstruction is carried out to measurement image.Not only realize
It is calculated every to the three-dimensional reconstruction of measurement image, and directly by the calibration section of each structure light figure on measurement image
The depth value of a first position coordinate avoids three-dimensional the step of correcting, improves the efficiency of three-dimensional reconstruction.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this Shen
Some embodiments please for those of ordinary skill in the art without any creative labor, can be with
It obtains other drawings based on these drawings.
Fig. 1 is the flow diagram for the three-dimensional rebuilding method that one embodiment of the application provides；
Fig. 2 is the depth value measuring principle figure that one embodiment of the application provides；
Fig. 3 is the flow diagram for the three-dimensional rebuilding method that another embodiment of the application provides；
Fig. 4 is the flow diagram for the three-dimensional rebuilding method that the another embodiment of the application provides；
Fig. 5 is the flow diagram for the three-dimensional rebuilding method that the application another embodiment provides；
Fig. 6 is the structural schematic diagram for the three-dimensional reconstruction apparatus that one embodiment of the application provides；
Fig. 7 is the structural schematic diagram for the three-dimensional reconstruction apparatus that another embodiment of the application provides；
Fig. 8 is the structural schematic diagram for the terminal device that one embodiment of the application provides.
Specific embodiment
To keep the purposes, technical schemes and advantages of the embodiment of the present application clearer, below in conjunction with the embodiment of the present application
In attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is
Some embodiments of the present application, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall in the protection scope of this application.
The description and claims of this application and term " first ", " second ", " third ", " in above-mentioned attached drawing
The (if present)s such as four " are to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should manage
The data that solution uses in this way are interchangeable under appropriate circumstances, so as to embodiments herein described herein, such as can be with
Sequence other than those of illustrating or describing herein is implemented.In addition, term " includes " and " having " and their times
What is deformed, it is intended that cover it is non-exclusive include, for example, contain the process, method of a series of steps or units, system,
Product or equipment those of are not necessarily limited to be clearly listed step or unit, but may include be not clearly listed or for
The intrinsic other step or units of these process, methods, product or equipment.
Three-dimensional reconstruction is an important research field of computer vision, and establishes expression objective world in a computer
Virtual reality key technology, in terms of bio-identification, compared to traditional two dimensional model, threedimensional model have bigger area
Other space, the necessity that the acquiring technology of three-dimensional information has it to develop.In the prior art, structured light reconstruction method is above accounted in application
According to some superiority, however structured light reconstruction method in the prior art, the complicated and three-dimensional correction accuracy of reconstruction process require height, make
It is lower at the efficiency of three-dimensional reconstruction, to solve the above-mentioned problems, the embodiment of the present application provide a kind of three-dimensional rebuilding method, device,
Equipment and storage medium.
Hereinafter, the exemplary application scene to the embodiment of the present application is introduced.
3-D image, which is compared, has bigger difference space with two dimensional image, and three-dimensional reconstruction is for shooting video camera
Two dimensional image, be redeveloped into 3-D image, with the development of computer vision technique, three-dimensional reconstruction is widely used in army
With, it is civilian etc., such as: investigation monitoring, military posture show, environmental monitoring, geology and geomorphology mapping, road monitoring traffic are thin
Control etc. is led, this is based on, the embodiment of the present application provides a kind of three-dimensional rebuilding method, device, equipment and storage medium.
Fig. 1 is the flow diagram for the three-dimensional rebuilding method that one embodiment of the application provides, and this method can be by Three-dimensional Gravity
Device execution is built, which can be realized by way of software and/or hardware, such as: the device can be terminal device
Partly or entirely, terminal device can be PC, smart phone, user terminal, tablet computer etc., below with terminal device
Three-dimensional rebuilding method is illustrated for executing subject, as shown in Figure 1, the method in the embodiment of the present invention may include:
Step S101: each corresponding first position coordinate of structure light figure on measurement image is obtained.
Measuring image is the structure light image to three-dimensional reconstruction, and structure light is to project testee surface by the projector
Initiating structure information, the embodiment of the present application to structure light figure with no restrictions, for example, structure light figure can be laser strip
Line, Gray code, sine streak, hot spot etc..After projector projective structure light to testee surface, pass through single or multiple cameras
Shooting measured surface obtains structure light image, i.e. measurement image.
It measures on image there are multiple structure light figures, obtains each structure light figure on measurement image corresponding the
One position coordinates, wherein each corresponding first position coordinate of structure light figure can be a certain solid of structure light figure
The pixel coordinate in measurement image is set in positioning, and the embodiment of the present application with no restrictions, such as can be structure light to the fixation position
The central point etc. of figure.Structure light figure can be single hot spot in structure light and project the one of sensor after face reflects
After a or multiple pixels, by this one or several pixel output signal formed measurement image in topography.
Step S102: according to measurement image, the first calibration maps and the second calibration maps, each structure light on measurement image is determined
The calibration section of figure.
First calibration maps are the calibration figures demarcated on the first calibration face, and the second calibration maps are in the second calibration face
The calibration figure of upper calibration, the first calibration face, the second calibration face are parallel with camera plane.First calibration face and the second calibration
The position in face, the quality for the image that can be shot according to camera and user demand are chosen, and the embodiment of the present application is to calibration
The specific location in face and choose mode with no restrictions, such as: it is directed to face identification system, the operating distance of the system is 20-
100 centimetres, then the first calibration face and the second calibration face can choose the arbitrary plane apart from 20-100 centimetres of camera plane, than
Such as, the first calibration face is apart from 40 centimeters of camera plane, i.e., the first calibration distance is 40 centimetres, and the second calibration face is apart from phase
80 centimeters of machine plane, i.e., the second calibration distance is 80 centimetres etc., and the above is only the exemplary introduction chosen to calibration face, this Shens
Please embodiment calibration face choose it is without being limited thereto.
After determining the first calibration face and the second calibration face, one piece of scaling board, the application are placed at the first calibration face
Embodiment to type, size of scaling board etc. with no restrictions, for example, calibration plate pattern be chessboard trrellis diagram；Then a band is shot
The calibration maps of structure light, obtain the first calibration maps, the embodiment of the present application to the acquisition modes of the first calibration maps with no restrictions, it is similar
, the calibration maps of a band structure light can be shot again, are obtained by moving scaling board to the second calibration face along camera optical axis
Second calibration maps, the embodiment of the present application are without limitation.Wherein, image, the first calibration maps and the second calibration maps are measured to be adopted
Structure light is identical structure light, such as can be the same structure light that the same dot matrix projector projects.
After getting the first calibration maps and the second calibration maps, according to measurement image, the first calibration maps and the second calibration maps
Determine the calibration section of each structure light figure on measurement image.How the embodiment of the present application is to according to measurement image, the first mark
Fixed figure and the second calibration maps determine the specific embodiment in the calibration section of each structure light figure on measurement image with no restrictions.
For the ease of introducing the calibration section of each structure light image, Fig. 2 is the depth value that one embodiment of the application provides
Measuring principle figure, as shown in Fig. 2, projector projective structure light to camera shoots space, wherein Z indicates that object plane is flat to camera
The distance in face, Z1 indicate first calibration distance, Z2 indicate second calibration distance, due to the first calibration maps, the second calibration maps and
Distance of the object plane apart from camera plane is different, therefore, the position of structure light figure can have parallax.And it is directed to the same knot
There are corresponding structure light figure and structure lights in measurement image, the first calibration maps and the second calibration maps for structure light figure
The position coordinates of figure.For example, the structure light figure on the position F in the first calibration maps, the structure on object plane location of C
Light figure and the structure light figure on the location A in the second calibration maps are mutually matched, and in measurement image, position F is corresponding
F ' in measurement image, position C correspond to the C ' in measurement image, and position A corresponds to the A ' in measurement image, wherein F '
It is the calibration section of the structure light figure with the line segment that A ' is formed by connecting, and the coordinate position of the structure light figure is corresponding at its
It demarcates on section, it, can be in each structure light figure pair by calculating the calibration section of each structure light figure on measurement image
The structure light figure is searched in the calibration section answered, and avoids three-dimensional rectification step in the prior art, Three-dimensional Gravity can be improved
The efficiency built.
Step S103: according to the calibration section of each structure light figure on measurement image, each first position coordinate is calculated
Depth value.
According to the calibration section of each structure light figure on measurement image, the depth of each first position coordinate can be calculated
Value, the embodiment of the present application calculate the depth value of each first position coordinate to how according to the calibration section on measurement image
Specific embodiment is with no restrictions.
In a kind of possible embodiment, as shown in Fig. 2, due to the first calibration face, the second calibration face and camera plane
It is parallel to each other, in order to calculate distance Z of the depth value i.e. object plane of each position coordinates apart from camera plane, according to triangle phase
Like principle, it is known that:
Therefore, available:
(Z2-Z1) * (C ' A ') * Z=Z1* (F ' A ') * (Z2-Z) (2)
Finally obtain depth value calculation formula:
Therefore, the depth value of each first position coordinate can be calculated by above-mentioned calculation formula (3).
In a kind of possible embodiment, according to the calibration section of each structure light figure of measurement image, calculate every
The depth value of a first position coordinate, comprising:
Determine each structure light figure in the first parallax of measurement image and the first calibration maps.In each structure light figure
It demarcates in section, determines that the section in addition to the first parallax is the second parallax, the second parallax is that the structure light figure is schemed in measurement
As the parallax with the second calibration maps.According to the first parallax and the second parallax, the depth value of each first position coordinate is calculated.
Determine each structure light figure in the first parallax of measurement image and the first calibration maps, such as the C ' A ' in Fig. 2, by
In the calibration section F ' A ' of known structure light image, therefore the structure light figure can be calculated in measurement image and the second mark
The the second parallax F ' C ' for determining figure, since the first calibration distance Z1 and the second calibration distance Z2 is it is known that being calculated according to depth value public
Formula can calculate the depth value of the first position coordinate of structure light figure.
It is similar, can also by each structure light figure of determination measurement image and the second calibration maps the second parallax,
Then according to the calibration section of each structure light, each structure light figure is obtained in the first view of measurement image and the first calibration maps
Difference, and then according to depth value calculation formula, obtain the depth value of the first position coordinate of the structure light figure.
Step S104: according to the depth value of each first position coordinate and calibration reconstruction parameter, three are carried out to measurement image
Dimension is rebuild.
After the depth value for determining each first position coordinate, according to calibration reconstruction parameter, first position coordinate is calculated
Three-dimensional coordinate, realize that the embodiment of the present application do not do the specific implementation of three-dimensional reconstruction to the three-dimensional reconstruction of measurement image
Limitation, meanwhile, all with no restrictions to specific calibration reconstruction parameter.
Three-dimensional rebuilding method provided by the embodiments of the present application, by according to measurement image, the first calibration maps and the second calibration
Figure determines that the calibration section of upper each structure light figure is schemed in measurement, then according to the mark of each structure light figure on measurement image
Determine section, calculate the depth value of each first position coordinate, finally according to the depth value of each first position coordinate and calibration weight
Parameter is built, three-dimensional reconstruction is carried out to measurement image, not only realizes the three-dimensional reconstruction to measurement image, but also directly pass through measurement
The calibration section of each structure light figure on image, calculates the depth value of each first position coordinate, avoids three-dimensional correction
Step improves the efficiency of three-dimensional reconstruction.
Optionally, Fig. 3 is the flow diagram for the three-dimensional rebuilding method that another embodiment of the application provides, and this method can be with
It is executed by three-dimensional reconstruction apparatus, which can be realized by way of software and/or hardware, such as: the device can be end
Some or all of end equipment, terminal device can be PC, smart phone, user terminal, tablet computer etc., below with
Terminal device is that executing subject is illustrated three-dimensional rebuilding method, as shown in figure 3, the application is implemented before step S103
Example provide three-dimensional rebuilding method, can also include:
Step S201: obtaining third calibration maps and the 4th calibration maps, third calibration maps are demarcated on the first calibration face
Non-structural light calibration maps, the 4th calibration maps are the non-structural light calibration maps demarcated on the second calibration face.
Third calibration maps are obtained, it can be by placing scaling board at the first calibration face, the embodiment of the present application is to scaling board
Type, size etc. with no restrictions, for example, calibration plate pattern is chessboard trrellis diagram；Then a calibration maps are shot, third mark is obtained
Fixed figure, the embodiment of the present application to the acquisition modes of third calibration maps with no restrictions, it is similar, can be by being moved along camera optical axis
Scaling board shoots a calibration maps again, obtains the 4th calibration maps, the embodiment of the present application does not limit this to the second calibration face
System.
Step S202: according to third calibration maps, the 4th calibration maps and camera imaging model, calibration reconstruction parameter is determined.
The application determines that ginseng is rebuild in calibration to how according to third calibration maps, the 4th calibration maps and camera imaging model
Several specific embodiments are with no restrictions.Illustratively, a kind of camera imaging model is introduced below, camera imaging model
Are as follows:
Wherein, u indicates that the abscissa under pixel planes coordinate system, v indicate the ordinate under pixel planes coordinate system, K table
Show that camera internal reference matrix, R indicate that spin matrix, T indicate translation vector, xwIndicate the X axis coordinate value under world coordinate system, yw
Indicate the Y axis coordinate value under world coordinate system, zwIndicate the Z axis coordinate value under world coordinate system.Therefore, in a kind of possibility
Embodiment in, can determine calibration reconstruction parameter by calculating K [R | T].
In alternatively possible embodiment, above-mentioned formula can further be derived, whereinIt obtains:
Wherein, fx, fy are parameters related with camera focus, the size of pixel, and cx, cy are camera photocentres in pixel planes
On coordinate, r1~r9 be spin matrix parameter, Tx, Ty, Tz is respectively X, the translation parameters on tri- directions Y, Z.Singly answer square
Battle array H is the homography matrix of Z=0 plane, and Δ H is Z=zwWhen homography matrix Increment Matrix, (H+zwΔ H) indicate Z=zwPlane
Homography matrix.Therefore calibration reconstruction parameter can be determined by the value of calculating H and Δ H.
On the basis of above-mentioned formula, in a kind of possible embodiment, calibration reconstruction parameter, root are determined in order to realize
According to third calibration maps, the 4th calibration maps and camera imaging model, calibration reconstruction parameter is determined, comprising:
In third calibration maps and the 4th calibration maps, multiple groups pixel coordinate and the corresponding calibration of multiple groups pixel coordinate are obtained
Coordinate on plate；It, respectively will be on every group of pixel coordinate and the corresponding scaling board of every group of pixel coordinate for multiple groups pixel coordinate
Coordinate, input camera imaging model in, to determine the homography matrix of plane arbitrarily parallel with camera plane in pre-set space.
In third calibration maps and the 4th calibration maps, multiple groups pixel coordinate (ui, v are obtained respectivelyi) and multiple groups pixel seat
The coordinate (xi, yi) on corresponding scaling board is marked, wherein i is the integer greater than zero, (ui, vi) indicate that i-th group of pixel is sat
Mark, with no restrictions to the numerical value of i, in a kind of possible embodiment, i is the integer more than or equal to 8 to the embodiment of the present application.Point
Not by pixel coordinate (ui, vi) with the corresponding scaling board of pixel coordinate on coordinate (xi, yi), bring into formula (5), really
Order answers matrix H and homography matrix Δ H.
Correspondingly, being carried out to measurement image three-dimensional according to the depth value of each first position coordinate and calibration reconstruction parameter
It rebuilds, comprising:
It is answered according to the list of plane arbitrarily parallel with camera plane in the depth value of each first position coordinate, pre-set space
Matrix and camera imaging model carry out three-dimensional reconstruction to measurement image.
According to the depth value Z=z of first position coordinatew, homography matrix H, homography matrix Δ H, first position coordinate (u, v)
And formula (5), calculate (xw, yw), finally determine the (x of each first position coordinatew, yw, zw), realize three to measurement image
Dimension is rebuild.
Due to by the pixel coordinate and the corresponding scaling board of pixel coordinate in third calibration maps and the 4th calibration maps
Coordinate, determine the homography matrix of plane arbitrarily parallel with camera plane in pre-set space, realize in pre-set space appoint
The determination of the three-dimensional coordinate for the plane parallel with camera plane of anticipating, and then realize the three-dimensional reconstruction to measurement image.Moreover, logical
It crosses the first calibration maps and the second calibration maps demarcates depth value, then pass through third calibration maps and the 4th calibration maps and phase
Machine imaging model determines calibration reconstruction parameter, realizes the separation of depth value calibration with calibration reconstruction parameter, reduces calibration
Required precision thereby reduces calibration difficulty.
In order to realize the determination to the calibration section of each structure light image on measurement image, in a kind of possible embodiment party
In formula, Fig. 4 is the flow diagram for the three-dimensional rebuilding method that the another embodiment of the application provides, and this method can be by three-dimensional reconstruction
Device executes, which can be realized by way of software and/or hardware, such as: the device can be the portion of terminal device
Divide or all, terminal device can be PC, smart phone, user terminal, tablet computer etc., be with terminal device below
Executing subject is illustrated three-dimensional rebuilding method, as shown in figure 4, step S102 may include:
Step S301: the structure light figure in matching measurement image, the first calibration maps and the second calibration maps.
Structure light figure in matching measurement image, the first calibration maps and the second calibration maps determines measurement image, the first mark
Corresponding structure light figure in fixed figure and the second calibration maps, how the embodiment of the present application is to matching measurement image, the first calibration maps
With no restrictions with the specific embodiment of the structure light figure in the second calibration maps.
Step S302: determine each structure light figure measurement image in first position coordinate, in the first calibration maps
Second position coordinate and the third place coordinate in the second calibration maps.
The application to the specific embodiment of this step with no restrictions, as long as can determine that each structure light figure is measuring
First position coordinate in image is sat in the second position coordinate in the first calibration maps and the third place in the second calibration maps
Mark.
Step S303: according to the first position coordinate, second position coordinate and the third place coordinate of each structure light figure,
Determine the calibration section of each structure light figure on measurement image.
As shown in Fig. 2, according to the first position coordinate, second position coordinate and the third place coordinate of each structure light, really
Surely the calibration section for measuring each structure light figure on image, can calculate F ' A ' according to Similar Principle of Triangle, this
Apply for that embodiment is without limitation.
In order to realize the determination to the calibration section of each structure light image on measurement image, in alternatively possible implementation
In mode, Fig. 5 is the flow diagram for the three-dimensional rebuilding method that the application another embodiment provides, and this method can be by Three-dimensional Gravity
Device execution is built, which can be realized by way of software and/or hardware, such as: the device can be terminal device
Partly or entirely, terminal device can be PC, smart phone, user terminal, tablet computer etc., below with terminal device
Three-dimensional rebuilding method is illustrated for executing subject, as shown in figure 5, step S102 may include:
Step S401: the structure light figure of matching the first calibration maps and the second calibration maps determines the first calibration maps and second
The coordinate correspondence relationship of each structure light figure in calibration maps.
The structure light figure for matching the first calibration maps and the second calibration maps determines every in the first calibration maps and the second calibration maps
The coordinate correspondence relationship of a structure light figure, wherein the coordinate pair of the first calibration maps and each structure light figure in the second calibration maps
Should be related to can be indicated by the way of homography matrix.
Step S402: the structure light figure of matching measurement image and the first calibration maps determines that each structure light figure is being surveyed
First position coordinate in spirogram picture and the second position coordinate in the first calibration maps.
The structure light figure of matching measurement image and the first calibration maps determines each structure light figure in measurement image
First position coordinate and the second position coordinate in the first calibration maps, specific matching way of the embodiment of the present application to this step
With no restrictions.
Step S403: according to every in first position coordinate, second position coordinate and the first calibration maps and the second calibration maps
The coordinate correspondence relationship of a structure light figure determines the calibration section of each structure light figure on measurement image.
It, can be according to each structure light figure in second position coordinate and the first calibration maps and the second calibration maps in this step
Coordinate correspondence relationship, the third place coordinate is determined, then according to the first position coordinate of each structure light figure, the second position
Coordinate and the third place coordinate determine the calibration section of each structure light figure on measurement image, specifically refer to step 303,
It repeats no more.
It should be noted that in the present embodiment, not done to calibration maps represented by the first calibration maps and the second calibration maps
It limits, the first calibration maps in step S402 can also be expressed as the second calibration maps.Due to by determining the first calibration maps and the
The coordinate correspondence relationship of each structure light figure in two calibration maps, it is only necessary to determine the position of structure light figure row in any calibration maps
Coordinate can be realized the determination to the position coordinates of counter structure light figure in another calibration maps, realize to nominal data
Compression, has saved a large amount of memory space.
It is following be device provided by the embodiments of the present application, equipment, storage medium and computer program product embodiments, can
For executing embodiment of the present invention method.For undisclosed details in the application Installation practice, the application side is please referred to
Method embodiment.
Fig. 6 is the structural schematic diagram for the three-dimensional reconstruction apparatus that one embodiment of the application provides, which can pass through software
And/or the mode of hardware is realized, and such as: the device can be some or all of terminal device, and terminal device can be individual
Computer, smart phone, user terminal, tablet computer etc., as shown in fig. 6, three-dimensional reconstruction apparatus provided by the embodiments of the present application can
To include:
First obtains module 61, sits for obtaining each corresponding first position of structure light figure on measurement image
Mark.
First determining module 62, for determining on measurement image according to measurement image, the first calibration maps and the second calibration maps
The calibration section of each structure light figure, the first calibration maps are the calibration figure demarcated on the first calibration face, the second mark
Determining figure is the calibration figure demarcated on the second calibration face, and the first calibration face, the second calibration face are parallel with camera plane.
Optionally, the first determining module 62, is specifically used for:
Structure light figure in matching measurement image, the first calibration maps and the second calibration maps.
Determine first position coordinate of each structure light figure in measurement image, the second position in the first calibration maps
Coordinate and the third place coordinate in the second calibration maps.
According to the first position coordinate, second position coordinate and the third place coordinate of each structure light figure, measurement is determined
The calibration section of each structure light figure on image.
Optionally, the first determining module 62, is specifically used for:
The structure light figure for matching the first calibration maps and the second calibration maps determines every in the first calibration maps and the second calibration maps
The coordinate correspondence relationship of a structure light figure.
The structure light figure of matching measurement image and the first calibration maps determines each structure light figure in measurement image
First position coordinate and the second position coordinate in the first calibration maps.
According to each structure light figure in first position coordinate, second position coordinate and the first calibration maps and the second calibration maps
The coordinate correspondence relationship of shape determines the calibration section of each structure light figure on measurement image.
Second determining module 63 calculates each for the calibration section according to each structure light figure on measurement image
The depth value of one position coordinates.
Optionally, the second determining module 63, is specifically used for:
Determine each structure light figure in the first parallax of measurement image and the first calibration maps.
In the calibration section of each structure light figure, determine that section in addition to the first parallax is the second parallax, second
Parallax is parallax of the structure light figure in measurement image and the second calibration maps.
According to the first parallax and the second parallax, the depth value of each first position coordinate is calculated.
Module 64 is rebuild, for the depth value and calibration reconstruction parameter according to each first position coordinate, to measurement image
Carry out three-dimensional reconstruction.
Optionally, Fig. 7 is the structural schematic diagram for the three-dimensional reconstruction apparatus that another embodiment of the application provides, which can be with
It is realized by way of software and/or hardware, such as: the device can be some or all of terminal device, and terminal device can
To be PC, smart phone, user terminal, tablet computer etc., as shown in fig. 7, Three-dimensional Gravity provided by the embodiments of the present application
Building device can also include:
Second obtains module 71, and for obtaining third calibration maps and the 4th calibration maps, third calibration maps are in the first calibration
The non-structural light calibration maps demarcated on face, the 4th calibration maps are the non-structural light calibration maps demarcated on the second calibration face.
Third determining module 72, for determining calibration according to third calibration maps, the 4th calibration maps and camera imaging model
Reconstruction parameter.
Optionally, third determining module 72, is specifically used for:
In third calibration maps and the 4th calibration maps, multiple groups pixel coordinate and the corresponding calibration of multiple groups pixel coordinate are obtained
Coordinate on plate.
For multiple groups pixel coordinate, respectively by the seat on every group of pixel coordinate and the corresponding scaling board of every group of pixel coordinate
Mark inputs in camera imaging model, to determine the homography matrix of plane arbitrarily parallel with camera plane in pre-set space.
It is specifically used for correspondingly, rebuilding module 64:
It is answered according to the list of plane arbitrarily parallel with camera plane in the depth value of each first position coordinate, pre-set space
Matrix and camera imaging model carry out three-dimensional reconstruction to measurement image.
The embodiment of the present application provides a kind of terminal device, and Fig. 8 is the structure for the terminal device that one embodiment of the application provides
Schematic diagram, as shown in figure 8, the terminal device includes:
Processor 81, memory 82, transceiver 83 and computer program；Wherein, transceiver 83 realizes vehicle-mounted radio
Data transmission between other equipment, computer program is stored in memory 82, and is configured as by processor 81
It executes, computer program includes the instruction for executing above-mentioned three-dimensional rebuilding method method, and content and effect please refer to method
Embodiment.
In addition, the embodiment of the present application also provides a kind of computer readable storage medium, deposited in computer readable storage medium
Computer executed instructions are contained, when at least one processor of user equipment executes the computer executed instructions, user equipment
Execute above-mentioned various possible methods.
Wherein, computer-readable medium includes computer storage media and communication media, and wherein communication media includes being convenient for
From a place to any medium of another place transmission computer program.Storage medium can be general or specialized computer
Any usable medium that can be accessed.A kind of illustrative storage medium is coupled to processor, to enable a processor to from this
Read information, and information can be written to the storage medium.Certainly, storage medium is also possible to the composition portion of processor
Point.Pocessor and storage media can be located in ASIC.In addition, the ASIC can be located in user equipment.Certainly, processor and
Storage medium can also be used as discrete assembly and be present in communication equipment.
Those of ordinary skill in the art will appreciate that: realize that all or part of the steps of above-mentioned each method embodiment can lead to
The relevant hardware of program instruction is crossed to complete.Program above-mentioned can be stored in a computer readable storage medium.The journey
When being executed, execution includes the steps that above-mentioned each method embodiment to sequence；And storage medium above-mentioned include: ROM, RAM, magnetic disk or
The various media that can store program code such as person's CD.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations；To the greatest extent
Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to
So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into
Row equivalent replacement；And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme.
Claims (16)
1. a kind of three-dimensional rebuilding method characterized by comprising
Each corresponding first position coordinate of structure light figure on measurement image is obtained, the measurement image is structure light figure
Picture, the structure light figure are the spot pattern of any structure light in the structure light image；
According to the measurement image, the first calibration maps and the second calibration maps, each structure light figure on the measurement image is determined
Calibration section, first calibration maps be by the first calibration face place scaling board shooting calibration figure, institute
Stating the second calibration maps is the calibration figure by placing the scaling board shooting on the second calibration face, first calibration
Face, second calibration face are parallel with camera plane, and the camera plane is the plane vertical with camera optical axis；
According to the calibration section of each structure light figure on the measurement image, the depth of each first position coordinate is calculated
Value；
According to the depth value of each first position coordinate and calibration reconstruction parameter, Three-dimensional Gravity is carried out to the measurement image
It builds.
2. the method according to claim 1, wherein according to the depth value of each first position coordinate and
Reconstruction parameter is demarcated, before measurement image progress three-dimensional reconstruction, further includes:
Obtain third calibration maps and the 4th calibration maps, the third calibration maps be demarcated on the first calibration face it is non-structural
Light calibration maps, the 4th calibration maps are the non-structural light calibration maps demarcated on the second calibration face；
According to the third calibration maps, the 4th calibration maps and camera imaging model, the calibration reconstruction parameter is determined.
3. according to the method described in claim 2, it is characterized in that, it is described according to the third calibration maps, it is described 4th calibration
Figure and camera imaging model determine calibration reconstruction parameter, comprising:
In the third calibration maps and the 4th calibration maps, multiple groups pixel coordinate and the multiple groups pixel coordinate pair are obtained
The coordinate on scaling board answered；
For the multiple groups pixel coordinate, respectively by the seat on every group of pixel coordinate and the corresponding scaling board of every group of pixel coordinate
Mark, inputs in the camera imaging model, to determine the homography matrix of plane arbitrarily parallel with camera plane in pre-set space；
Correspondingly, being carried out according to the depth value of each first position coordinate and calibration reconstruction parameter to the measurement image
Three-dimensional reconstruction, comprising:
According to plane arbitrarily parallel with camera plane in the depth value of each first position coordinate, the pre-set space
Homography matrix and the camera imaging model carry out three-dimensional reconstruction to the measurement image.
4. according to the method described in claim 3, it is characterized in that, according to the measurement image, the first calibration maps and the second mark
Fixed figure determines the calibration section of each structure light figure on the measurement image, comprising:
Match the structure light figure in the measurement image, first calibration maps and second calibration maps；
Determine each structure light figure in the first position coordinate measured in image, second in first calibration maps
Position coordinates and the third place coordinate in second calibration maps；
According to the first position coordinate, second position coordinate and the third place coordinate of each structure light figure, the measurement is determined
The calibration section of each structure light figure on image.
5. according to the method described in claim 3, it is characterized in that, described according to the measurement image, the first calibration maps and
Two calibration maps determine the calibration section of each structure light figure on the measurement image, comprising:
The structure light figure for matching first calibration maps and second calibration maps determines first calibration maps and described the
The coordinate correspondence relationship of each structure light figure in two calibration maps；
The structure light figure for matching the measurement image and first calibration maps, determines each structure light figure in the measurement
First position coordinate in image and the second position coordinate in first calibration maps；
According to each in the first position coordinate, second position coordinate and first calibration maps and second calibration maps
The coordinate correspondence relationship of structure light figure determines the calibration section of each structure light figure on the measurement image.
6. method according to claim 1-5, which is characterized in that each knot according to the measurement image
The calibration section of structure light figure calculates the depth value of each first position coordinate, comprising:
Determine each structure light figure in the first parallax of the measurement image and first calibration maps；
In the calibration section of each structure light figure, determine that section in addition to the first parallax is the second parallax, described second
Parallax is parallax of the structure light figure in the measurement image and second calibration maps；
According to first parallax and second parallax, the depth value of each first position coordinate is calculated.
7. method according to claim 1-5, which is characterized in that
The first calibration face and the second calibration face are located at the two sides or first calibration face and described of object plane
Second calibration face is located at the same side of the object plane.
8. a kind of three-dimensional reconstruction apparatus characterized by comprising
First obtains module, described for obtaining each corresponding first position coordinate of structure light figure on measurement image
Measurement image is structure light image, and the structure light figure is the spot pattern of any structure light in the structure light image；
First determining module, for determining the measurement image according to the measurement image, the first calibration maps and the second calibration maps
The calibration section of upper each structure light figure, first calibration maps are shot by placing scaling board on the first calibration face
Calibration figure, second calibration maps are the calibrations by placing the scaling board shooting on the second calibration face
Figure, first calibration face, second calibration face are parallel with camera plane, and the camera plane is vertical with camera optical axis
Plane；
Second determining module calculates each described for the calibration section according to each structure light figure on the measurement image
The depth value of first position coordinate；
Module is rebuild, for the depth value and calibration reconstruction parameter according to each first position coordinate, the measurement is schemed
As carrying out three-dimensional reconstruction.
9. device according to claim 8, which is characterized in that further include:
Second obtains module, and for obtaining third calibration maps and the 4th calibration maps, the third calibration maps are in first mark
Determine the non-structural light calibration maps demarcated on face, the 4th calibration maps are the non-structural cursors demarcated on the second calibration face
Fixed figure；
Third determining module, for determining institute according to the third calibration maps, the 4th calibration maps and camera imaging model
State calibration reconstruction parameter.
10. device according to claim 9, which is characterized in that the third determining module is specifically used for:
In the third calibration maps and the 4th calibration maps, multiple groups pixel coordinate and the multiple groups pixel coordinate pair are obtained
The coordinate on scaling board answered；
For the multiple groups pixel coordinate, respectively by the seat on every group of pixel coordinate and the corresponding scaling board of every group of pixel coordinate
Mark, inputs in the camera imaging model, to determine the homography matrix of plane arbitrarily parallel with camera plane in pre-set space；
Correspondingly, the reconstruction module is specifically used for:
According to plane arbitrarily parallel with camera plane in the depth value of each first position coordinate, the pre-set space
Homography matrix and the camera imaging model carry out three-dimensional reconstruction to the measurement image.
11. device according to claim 10, which is characterized in that first determining module is specifically used for:
Match the structure light figure in the measurement image, first calibration maps and second calibration maps；
Determine each structure light figure in the first position coordinate measured in image, second in first calibration maps
Position coordinates and the third place coordinate in second calibration maps；
According to the first position coordinate, second position coordinate and the third place coordinate of each structure light figure, the measurement is determined
The calibration section of each structure light figure on image.
12. device according to claim 10, which is characterized in that first determining module is specifically used for:
The structure light figure for matching first calibration maps and second calibration maps determines first calibration maps and described the
The coordinate correspondence relationship of each structure light figure in two calibration maps；
The structure light figure for matching the measurement image and first calibration maps, determines each structure light figure in the measurement
First position coordinate in image and the second position coordinate in first calibration maps；
According to each in the first position coordinate, second position coordinate and first calibration maps and second calibration maps
The coordinate correspondence relationship of structure light figure determines the calibration section of each structure light figure on the measurement image.
13. according to the described in any item devices of claim 8-12, which is characterized in that second determining module is specifically used for:
Determine each structure light figure in the first parallax of the measurement image and first calibration maps；
In the calibration section of each structure light figure, determine that section in addition to the first parallax is the second parallax, described second
Parallax is parallax of the structure light figure in the measurement image and second calibration maps；
According to first parallax and second parallax, the depth value of each first position coordinate is calculated.
14. according to the described in any item devices of claim 8-12, which is characterized in that
The first calibration face and second calibration face are located at the two sides or first calibration face and described second of object plane
Calibration face is located at the side of the object plane.
15. a kind of equipment characterized by comprising
Processor；
Memory；And
Computer program；
Wherein, the computer program is stored in the memory, and is configured as being executed by the processor, described
Computer program includes the instruction for executing the method according to claim 1 to 7.
16. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has computer journey
Sequence, the computer program make server perform claim require the described in any item methods of 1-7.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2019/088698 WO2020237492A1 (en) | 2019-05-28 | 2019-05-28 | Three-dimensional reconstruction method, device, apparatus, and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110337674A true CN110337674A (en) | 2019-10-15 |
| CN110337674B CN110337674B (en) | 2023-07-07 |
Family
ID=68150224
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201980000842.8A Active CN110337674B (en) | 2019-05-28 | 2019-05-28 | Three-dimensional reconstruction method, device, equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110337674B (en) |
| WO (1) | WO2020237492A1 (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112686961A (en) * | 2020-12-31 | 2021-04-20 | 杭州海康机器人技术有限公司 | Method and device for correcting calibration parameters of depth camera |
| CN113251951A (en) * | 2021-04-26 | 2021-08-13 | 黄淮学院 | Calibration method of line structured light vision measurement system based on single calibration surface mapping |
| CN113379849A (en) * | 2021-06-10 | 2021-09-10 | 南开大学 | Robot autonomous recognition intelligent grabbing method and system based on depth camera |
| US20220065881A1 (en) * | 2020-08-31 | 2022-03-03 | Sysmex Corporation | Calibration curve setting method, specimen analysis method, calibration curve setting program, specimen analysis program, and specimen analyzer |
| US11965899B2 (en) * | 2020-08-31 | 2024-04-23 | Sysmex Corporation | Calibration curve setting method, specimen analysis method, calibration curve setting program, specimen analysis program, and specimen analyzer |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112581605A (en) * | 2020-12-24 | 2021-03-30 | 西安中科光电精密工程有限公司 | Structured light three-dimensional reconstruction correction method and device |
| CN114359894A (en) * | 2022-01-13 | 2022-04-15 | 浙大城市学院 | Buddhist image cultural relic three-dimensional model identification and classification method |
| CN115115788B (en) * | 2022-08-12 | 2023-11-03 | 梅卡曼德（北京）机器人科技有限公司 | Three-dimensional reconstruction method and device, electronic equipment and storage medium |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101697233A (en) * | 2009-10-16 | 2010-04-21 | 长春理工大学 | Structured light-based three-dimensional object surface reconstruction method |
| US20100182406A1 (en) * | 2007-07-12 | 2010-07-22 | Benitez Ana B | System and method for three-dimensional object reconstruction from two-dimensional images |
| US20130169643A1 (en) * | 2012-01-03 | 2013-07-04 | Samsung Electronics Co., Ltd. | Display apparatus and method for estimating depth |
| CN103424083A (en) * | 2012-05-24 | 2013-12-04 | 北京数码视讯科技股份有限公司 | Object depth detection method, device and system |
| CN103971405A (en) * | 2014-05-06 | 2014-08-06 | 重庆大学 | Method for three-dimensional reconstruction of laser speckle structured light and depth information |
| CN104346829A (en) * | 2013-07-29 | 2015-02-11 | 中国农业机械化科学研究院 | Three-dimensional color reconstruction system and method based on PMD (photonic mixer device) cameras and photographing head |
| CN104408732A (en) * | 2014-12-10 | 2015-03-11 | 东北大学 | Large-view-field depth measuring system and method based on omni-directional structured light |
| CN105160680A (en) * | 2015-09-08 | 2015-12-16 | 北京航空航天大学 | Design method of camera with no interference depth based on structured light |
| JP2016102755A (en) * | 2014-11-28 | 2016-06-02 | キヤノン株式会社 | Information processing device, information processing method and program |
| US20170310946A1 (en) * | 2016-04-21 | 2017-10-26 | Chenyang Ge | Three-dimensional depth perception apparatus and method |
| CN107607040A (en) * | 2017-08-11 | 2018-01-19 | 天津大学 | A kind of three-dimensional scanning measurement device and method suitable for High Reflective Surface |
| CN107945268A (en) * | 2017-12-15 | 2018-04-20 | 深圳大学 | A kind of high-precision three-dimensional method for reconstructing and system based on binary area-structure light |
| CN108088386A (en) * | 2017-12-15 | 2018-05-29 | 深圳大学 | The binary area-structure light detection method and system of a kind of micro-nano magnitude |
| CN108540717A (en) * | 2018-03-31 | 2018-09-14 | 深圳奥比中光科技有限公司 | Target image obtains System and method for |
| CN108709499A (en) * | 2018-04-28 | 2018-10-26 | 天津大学 | A kind of structured light vision sensor and its quick calibrating method |
| CN109087382A (en) * | 2018-08-01 | 2018-12-25 | 宁波发睿泰科智能科技有限公司 | A kind of three-dimensional reconstruction method and 3-D imaging system |
| CN109510948A (en) * | 2018-09-30 | 2019-03-22 | 先临三维科技股份有限公司 | Exposure adjustment method, device, computer equipment and storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103337071B (en) * | 2013-06-19 | 2016-03-30 | 北京理工大学 | The venae subcutaneae three-dimensional visualization device that structure based is rebuild and method |
| CN103971408B (en) * | 2014-05-21 | 2017-05-03 | 中国科学院苏州纳米技术与纳米仿生研究所 | Three-dimensional facial model generating system and method |
-
2019
- 2019-05-28 CN CN201980000842.8A patent/CN110337674B/en active Active
- 2019-05-28 WO PCT/CN2019/088698 patent/WO2020237492A1/en active Application Filing
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100182406A1 (en) * | 2007-07-12 | 2010-07-22 | Benitez Ana B | System and method for three-dimensional object reconstruction from two-dimensional images |
| CN101697233A (en) * | 2009-10-16 | 2010-04-21 | 长春理工大学 | Structured light-based three-dimensional object surface reconstruction method |
| US20130169643A1 (en) * | 2012-01-03 | 2013-07-04 | Samsung Electronics Co., Ltd. | Display apparatus and method for estimating depth |
| CN103424083A (en) * | 2012-05-24 | 2013-12-04 | 北京数码视讯科技股份有限公司 | Object depth detection method, device and system |
| CN104346829A (en) * | 2013-07-29 | 2015-02-11 | 中国农业机械化科学研究院 | Three-dimensional color reconstruction system and method based on PMD (photonic mixer device) cameras and photographing head |
| CN103971405A (en) * | 2014-05-06 | 2014-08-06 | 重庆大学 | Method for three-dimensional reconstruction of laser speckle structured light and depth information |
| JP2016102755A (en) * | 2014-11-28 | 2016-06-02 | キヤノン株式会社 | Information processing device, information processing method and program |
| CN104408732A (en) * | 2014-12-10 | 2015-03-11 | 东北大学 | Large-view-field depth measuring system and method based on omni-directional structured light |
| CN105160680A (en) * | 2015-09-08 | 2015-12-16 | 北京航空航天大学 | Design method of camera with no interference depth based on structured light |
| US20170310946A1 (en) * | 2016-04-21 | 2017-10-26 | Chenyang Ge | Three-dimensional depth perception apparatus and method |
| CN107607040A (en) * | 2017-08-11 | 2018-01-19 | 天津大学 | A kind of three-dimensional scanning measurement device and method suitable for High Reflective Surface |
| CN107945268A (en) * | 2017-12-15 | 2018-04-20 | 深圳大学 | A kind of high-precision three-dimensional method for reconstructing and system based on binary area-structure light |
| CN108088386A (en) * | 2017-12-15 | 2018-05-29 | 深圳大学 | The binary area-structure light detection method and system of a kind of micro-nano magnitude |
| CN108540717A (en) * | 2018-03-31 | 2018-09-14 | 深圳奥比中光科技有限公司 | Target image obtains System and method for |
| CN108709499A (en) * | 2018-04-28 | 2018-10-26 | 天津大学 | A kind of structured light vision sensor and its quick calibrating method |
| CN109087382A (en) * | 2018-08-01 | 2018-12-25 | 宁波发睿泰科智能科技有限公司 | A kind of three-dimensional reconstruction method and 3-D imaging system |
| CN109510948A (en) * | 2018-09-30 | 2019-03-22 | 先临三维科技股份有限公司 | Exposure adjustment method, device, computer equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 易双;何昭水;王沛涛;杨森泉;: "一种基于结构光的三维重建方法研究", 电子技术, no. 08 * |
| 贾小军;廖伟志;孙亚新;方玫;曾丹;: "结构光场光束直线跟踪的两步标定方法", 光电子・激光, no. 03 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220065881A1 (en) * | 2020-08-31 | 2022-03-03 | Sysmex Corporation | Calibration curve setting method, specimen analysis method, calibration curve setting program, specimen analysis program, and specimen analyzer |
| US11965899B2 (en) * | 2020-08-31 | 2024-04-23 | Sysmex Corporation | Calibration curve setting method, specimen analysis method, calibration curve setting program, specimen analysis program, and specimen analyzer |
| CN112686961A (en) * | 2020-12-31 | 2021-04-20 | 杭州海康机器人技术有限公司 | Method and device for correcting calibration parameters of depth camera |
| CN113251951A (en) * | 2021-04-26 | 2021-08-13 | 黄淮学院 | Calibration method of line structured light vision measurement system based on single calibration surface mapping |
| CN113251951B (en) * | 2021-04-26 | 2024-03-01 | 湖北汽车工业学院 | Calibration method of line structured light vision measurement system based on single calibration surface mapping |
| CN113379849A (en) * | 2021-06-10 | 2021-09-10 | 南开大学 | Robot autonomous recognition intelligent grabbing method and system based on depth camera |
| CN113379849B (en) * | 2021-06-10 | 2023-04-18 | 南开大学 | Robot autonomous recognition intelligent grabbing method and system based on depth camera |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020237492A1 (en) | 2020-12-03 |
| CN110337674B (en) | 2023-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11928838B2 (en) | Calibration system and method to align a 3D virtual scene and a 3D real world for a stereoscopic head-mounted display | |
| CN110337674A (en) | Three-dimensional rebuilding method, device, equipment and storage medium | |
| CN100417231C (en) | Three-dimensional vision semi-matter simulating system and method | |
| CN106101689B (en) | The method that using mobile phone monocular cam virtual reality glasses are carried out with augmented reality | |
| CN104322060B (en) | System, method and apparatus that low latency for depth map is deformed | |
| CN100485720C (en) | 360 degree around panorama generation method based on serial static image | |
| CN104330074B (en) | Intelligent surveying and mapping platform and realizing method thereof | |
| CN106504188B (en) | Generation method and device for the eye-observation image that stereoscopic vision is presented | |
| US20210209777A1 (en) | Method for displaying a virtual image, a virtual image display system and device, a non-transient computer-readable storage medium | |
| CN104778694B (en) | A kind of parametrization automatic geometric correction method shown towards multi-projection system | |
| CN104155765B (en) | The method and apparatus of revision for 3-D image in spliced integration imaging display | |
| CN108288292A (en) | A kind of three-dimensional rebuilding method, device and equipment | |
| CN110390719A (en) | Based on flight time point cloud reconstructing apparatus | |
| KR20090117531A (en) | System for constructing mixed reality and method thereof | |
| JP2020506487A (en) | Apparatus and method for obtaining depth information from a scene | |
| JPWO2018235163A1 (en) | Calibration apparatus, calibration chart, chart pattern generation apparatus, and calibration method | |
| CN111062869B (en) | Multi-channel correction splicing method for curved curtain | |
| CN109615664B (en) | Calibration method and device for optical perspective augmented reality display | |
| CN108513123A (en) | A kind of pattern matrix generation method that integration imaging light field is shown | |
| CN108063940B (en) | Correction system and method for human eye tracking naked eye 3D display system | |
| CN102831601A (en) | Three-dimensional matching method based on union similarity measure and self-adaptive support weighting | |
| CN108230384A (en) | Picture depth computational methods, device, storage medium and electronic equipment | |
| CN110335307A (en) | Scaling method, device, computer storage medium and terminal device | |
| CN105374067A (en) | Three-dimensional reconstruction method based on PAL cameras and reconstruction system thereof | |
| CN103260008B (en) | A kind of image position is to the projection conversion method of physical location |
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 |