CN104537705B - Mobile platform three dimensional biological molecular display system and method based on augmented reality - Google Patents
Mobile platform three dimensional biological molecular display system and method based on augmented reality Download PDFInfo
- Publication number
- CN104537705B CN104537705B CN201510033511.8A CN201510033511A CN104537705B CN 104537705 B CN104537705 B CN 104537705B CN 201510033511 A CN201510033511 A CN 201510033511A CN 104537705 B CN104537705 B CN 104537705B
- Authority
- CN
- China
- Prior art keywords
- pdb
- dimensional
- picture
- augmented reality
- mobile platform
- 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.)
- Expired - Fee Related
Links
Landscapes
- Processing Or Creating Images (AREA)
Abstract
The present invention relates to a kind of mobile platform three dimensional biological molecular display system and method based on augmented reality, the three-dimensional real-time exhibition of the identification and correspondence molecule to traditionally on paper printed article biomolecule two-dimension picture is realized on a mobile platform.Image characteristic point is detected for it and matching process is improved, and it is completed in mobile client and cloud server collaboration, improves flexibility, has saved client resource.Three-dimensional molecular modeling data derives from protein structural information database PDB (Protein Data Bank), it is ensured that accuracy and authority.The present invention is extended augmented reality, and a kind of typical case's application is proposed in terms of Biochemistry and Molecular Biology education and study, its technological means and framework can be applied to any field of Education and teaching, due to the development and popularization of mobile terminal, and its portable feature, user can whenever and wherever possible use the system, can greatly improve efficiency of teaching and learning interest.
Description
Technical field
The present invention is a kind of three-dimensional protein realized on a mobile platform, nucleic acid molecules real-time rendering, interaction and tracking
Technology, is related to the application of augmented reality.
Background technology
For a long time, preclinical medicine science, during especially subject as similar Biochemistry and Molecular Biology is teaching and research,
A maximum problem is exactly microcosmic property, the invisibility of research object.As genome times afterwards comprehensively, protein group epoch arrive
Come, this contradiction is increasingly protruded.The fast development requirement of subject grasps new theory and new technology as early as possible from, practitioner,
The traditional teaching using paper media as carrier, research meanses have not caught up with requirement.
Augmented reality (AR, augmented reality) technology is that a kind of utilization computer technology is seen to user
Real world carries out the technology of scene extension.AR comes from virtual reality (Virtual Reality, VR) technology, and the latter is to utilize
The technology of the behaviors such as vision, the sense of hearing, motion of the virtual environment simulation people true to nature of computer generation in natural environment.Therewith
Unlike, AR is again overlapped reality scene after analog simulation, and figure that it produces computer, word are by specifying
Position and attitude are fused in real scene, make user be immersed in it is true with virtual hybird environment in, produce a kind of new
Man-machine interaction mode.Augmented reality has become a key areas in virtual reality research, it military affairs, safety, industry,
The industries such as medical treatment, education and amusement have a wide range of applications.Augmented reality contains multimedia, three-dimensional modeling, reality
When video show and control, sensor, real-time tracking and registration, new technology and the new tool such as scene fusion.Augmented reality is provided
In general, different from the appreciable information of the mankind.
Be easy to carry present invention utilizes mobile platform, convenient use the characteristics of and high in the clouds data retrieval.In mobile terminal
It is complete to realize AR technologies, and be made that extension with reference to actual conditions and improve.The present invention is first by AR technologies and biomolecule
Three-dimensional display combines, three-dimensional according to making as three-dimensional molecular modeling using RCSB protein and nucleic acid structure information database
Model and animation, are that AR technologies propose a kind of typical case's realization in micro molecule teaching, simulation field.
The content of the invention
Present invention solves the technical problem that being：A kind of mobile platform three dimensional biological molecule virtual display based on augmented reality
Technology.High in the clouds clothes including the storage of picture feature point high in the clouds, recognition detection and Model Matching, based on the identification of picture feature point
Business device-Protein Data Bank data retrieval and transmission, the real-time rendering of mobile terminal biomolecule threedimensional model, mobile terminal are imaged
Head location position and scene drawing.
Instant invention overcomes the limitation that traditionally on paper media show to three-dimensional molecular structure and function, it is proposed that Yi Zhongquan
New three-dimensional molecular real-time exhibition technology and teaching means, overcome efficiency and speed that complex polygon shows in cell phone platform
Problem, is that AR technologies propose that a typical case realizes in micro molecule teaching, the application of simulation field.
The technical solution adopted by the present invention is：A kind of mobile platform three dimensional biological molecule virtual display based on augmented reality
Technology, including following five steps：
Step (1) picture feature point is extracted：Plane picture on teaching material is taken pictures or scanned, characteristic point data is extracted
And store in service end.
Step (2) PDB file acquisitions and treatment：Each pictures are specified with its PDB ID, server is with PDB ID
Retrieved in PDB, processed after obtaining pdb files, and stored in server, by Image ID and pdb files and picture
Relevant information is associated.
Step (3) picture recognition：Picture feature dot matrix is extracted in mobile terminal, and service end is uploaded at a time interval,
Characteristic point matrix in service end ergodic data storehouse carries out similarity-rough set.Set when two images Feature Points Matching quantity is more than
Think that two images are matched during fixed threshold value.
The drafting of step (4) three-dimensional separation flow：In mobile terminal, the three-dimensional atomic point in the PDB files for obtaining is sat
Mark, real-time rendering molecule C atomic framework ribbon models and surface three dimension model.
The Tracing Registration of step (5) view-based access control model mark：Mobile client end system by the model of generation in step (4) with take the photograph
As the true picture that head shoots is overlapped display.Camera is carried out when client camera position changes to re-scale, and is passed through
Coordinate transform real-time update visual angle, makes the observer can be from arbitrarily angled and apart from observing and nursing.
Present invention advantage compared with prior art is：
1. recognition efficiency and accuracy：The Feature point recognition method commonly used in AR technologies is Corner Detection, such as Roberts,
Sobel, Prewitt, Canny operator detection method etc..And in the books illustration of reality, necessarily have some picture feature points compared with
It is few, cannot extract effective characteristic point using these methods.Cause the decline of discrimination.In the present invention, picture feature point
Identification matching uses Surf algorithms.Surf algorithms are based on Sift algorithms, but are not required to carry out two to image when metric space is built
Secondary sampling, so as to improve algorithm performance.The characteristics of its is maximum is fast recognition speed.Under conditions of moderate, in completion two images
The matching of object realizes real-time processing substantially.With respect to other algorithms, being capable of effective identification feature point, the speed of identification and accurate
Rate has greatly improved.
2. the identification of plurality of pictures, Network Recognition：Traditional AR technologies are that identification picture is retained in locally as template,
Take up room big and dumb.And several specific pictures can only be recognized, it is of limited application.In the present invention, identification picture is made
For template is retained in cloud server, client volume occupancy is reduced, any plurality of pictures is can recognize that in theory；Picture recognition
Depend on network, the characteristic point data for really extracting that user end to server sends, its data volume very little, Ke Yili
It is simple text to solve, and can reduce network traffics, shorten transmission time.
3. three-dimensional separation flow real-time rendering：Traditional AR technologies usually first make threedimensional model to be shown, need
Will when shown and hidden.The present invention completes painting in real time for three-dimensional separation flow in mobile client using OpenGL ES
System.Server is processed corresponding PDB files, and a small amount of information is only only sent to client, and (three-dimensional molecular space is sat
Mark), further increase the real-time of identification；When needing to change model, transmission of coordinate file again is only needed, alleviate shifting
Moved end system burden.
4. the present invention is first by AR Technology applications in the three-dimensional real-time exhibition with biomolecule.
5. the characteristics of present invention is using mobile terminal portability, can use whenever and wherever possible, overcome real using desktop computer etc.
The limitation of existing AR technologies.
Brief description of the drawings
Fig. 1 is system principle of the invention and implementation schematic diagram；
Fig. 2 is processed for server will retrieve the pdb files for obtaining；
Fig. 3 is the picture feature Point matching schematic diagram that service end picture and client are photographed according to Surf methods；
Fig. 4 camera models use pin-hole model approximate representation, throwings of the center of gravity P of mark on image in true environment
Shadow position p, is the optical centre O and line OP of P points and the intersection point of the plane of delineation；
Fig. 5 is final result (human hemoglobin, PDB ID：2dhb).
Specific embodiment
The specific embodiment of the invention is illustrated below in conjunction with the accompanying drawings：
Step：
1. picture feature point is extracted
1.1 IMAQs：
With illustration in scanner or the form taken pictures acquisition book.
1.2 pictures are pre-processed：
S1：Gamma correction：Rgb value to each pixel is while a plus or minus specific value.
S2：：Gray scale transformation：By gray-scale map histogram, the number of pixels of each Pixel-level is calculated；Form accumulation Nogata
Figure, then carries out histogram equalization；Set up new brightness look-up table.
S3：Smoothing processing, to image length and width respectively × 2, and Gauss filtering is smoothed.
1.3Surf algorithms are realized and characteristic point generation：
This part is broadly divided into 5 steps：
S1：Hessian matrixes are built, replaces functional value f (x, y) with image pixel L (x, y), from second order standard gaussian
Function, by specific internuclear convolutional calculation second-order partial differential coefficient, just can so calculate H-matrix as wave filter, in formula, L xx
(x, σ), Lxy (x, σ), Lyy (x, σ) are the convolution of the second dervative of Gaussian function and image at X points.
S2：Build metric space：In Sift algorithms, previous tomographic image is depended on per tomographic image, and image needs weight
If size, therefore, this computational methods operand is larger, and Surf algorithms are different from Sift in terms of using pyramid.Algorithm
Allow metric space multi-layer image simultaneously processed, be not required to carry out secondary sample to image, so as to improve performance.
S3：Location feature point：A suitably default extreme value is determined, using corresponding with S2 mesoscale tomographic image resolutions
The wave filter of size is detected that the characteristic value of pixel can determine that the feature that the point is the region if more than surrounding pixel
Point.All values less than default extreme value are all dropped.
S4：Principal direction determines：Centered on characteristic point, calculating radius is the neighbour of 6s (S is characterized the scale-value at a place)
The Haar small echos (the Haar small echo length of sides take 4s) of point in domain in z, y direction are responded, and assign Gauss weight system to these responses
Number so that the response contribution near characteristic point is big, and the response contribution away from characteristic point is small, secondly by the response in the range of 60 °
New vector is summed to form, whole border circular areas are traveled through, the direction of most long vector is selected for the principal direction of this feature point.This
Sample, is calculated one by one by characteristic point, obtains the principal direction of each characteristic point.
S5：Generation feature point description：8 × 8 window is taken centered on key point.Try to achieve the gradient magnitude of each pixel
With gradient direction, it is computed weighted with Gauss window, each pixel correspondence one vector, then every 4 × 4 fritter
8 gradient orientation histograms in direction of upper calculating, draw the accumulated value of each gradient direction.
The preservation of 1.4 picture features vector
Features described above point vector information is stored in home server, Image ID is associated in database.
2.PDB file acquisitions and treatment
2.1PDB file acquisitions：When server background is uploaded per pictures, the PDB per pictures is specified manually
No. ID, server is retrieved according to this No. ID in RCSB PDB data base manipulation RCSB-PDB FETCH services services,
Due to No. ID uniquely, so the pdb files for obtaining are also unique.
2.2PDB file process：Original pdb files are generally large, include many redundancies, for reduce server and
Client network volume of transmitted data, server is pre-processed to the pdb files for retrieving.Sat comprising atom point in Pdb files
Target row is started with ATOM or HETATM.Find the row occurred for the first time with ATOM or HETATM. in file, since this journey by
Row deletion before, only retains the file of three-dimensional atomic point coordinates, as shown in Figure 2.
3. picture recognition and template matches
Mobile terminal is directed at picture by camera, catches scene, carries out that size is unitized and primary compression, with every
The picture that the speed of 10fps continues to capture carries out extracting characteristic point treatment, processing method same step (1) methods described.Carry
Service end is forwarded it to after getting image characteristic point, in service end, for a characteristic point on certain width image, using such as K-D
Tree algorithm finds minimum with the characteristic vector distance of point to be matched and time minimum characteristic point in another piece image.If minimum
Distance is less than certain threshold value with secondary minimum range ratio, then it is assumed that the point to be matched Point matching minimum with distance.Otherwise matching is not
Success.As shown in Fig. 2 left figure is service end picture, right figure is the picture that mobile terminal captured in real-time is arrived.Both carry out characteristic point
Threshold value of the quantity with (line) much larger than setting, it is believed that captured picture.
4. the Tracing Registration of view-based access control model mark, three-dimensional separation flow are drawn
S1：Camera position is demarcated：
This part be based primarily upon Qualcomm Vuforia FastCV increase income storehouse realization, now principle is illustrated：
Camera calibration technology is relevant with four coordinate systems, is respectively world coordinate system, and imaging plane coordinate system, camera is sat
Mark system and image displaing coordinate system.The three-dimensional body of real world is changed into the two-dimensional points of the plane of delineation by camera imaging principle
Process is, it is necessary to by the coordinate transform between four coordinate systems, camera calibration technology it needs to be determined that between these coordinate transforms
Transformation relation, then calculates this point in true three-dimension space using this relation according to the two-dimensional points on image manifesting planes
In position.
5 inner parameters and 6 external parameters of video camera are calculated first.
Camera model uses pin-hole model approximate representation, projections of the center of gravity P of mark on image in true environment
Position p is optical centre O and the intersection point of the line OP of P points and the plane of delineation, as shown in Figure 4.
Color sign point Xwi, Ywi, Zwi known to three dimensional space coordinate in world coordinate system.It is in camera coordinate system
In coordinate and the position in image image coordinates system can be represented with below equation.Wherein R, T are respectively spin matrix peace
Move vector.F is the focal length of video camera, and u0, v0 are image plane center coordinate, and △ x, △ y are neighbor pixel in horizontal and vertical side
To spacing.
Above formula includes 11 unknown parameters, 5 intrinsic parameters of the camera f, u0, v0, △ x, △ y altogether；6 outside ginsengs
Number R (Rx, Ry, Rz) and T (Tx, Ty, Tz).As long as therefore having 6, space images above point coordinates (ui, vi) whole can be obtained
Inside and outside parameter.
S2：Model, scene drawing
Protein structure has various drawing notations, most common to have wire-frame model (wireframe), rod model
(Bonds), ball-and-stick model (CpK), VDW models, the belt pattern that floats (Ribbon) and molecular surface model etc..
Wire-frame model (Wireframe)：Chemical bond between atom is represented with a straight line.
Rod model (Bond)：Chemical bond between atom is represented with a cylinder.
Ball-and-stick model (CPK)：Atom represents that chemical bond is represented with a cylinder with a spheroid.
Van der Waals model (VDW)：Atom represents that the radius of a ball is van der Waals radius with a spheroid.
Ribbon model (Ribbon)：To the banding of both sides uniform expansion centered on from the B-spline curves by all C atoms
Represent.
Molecular surface model (MolecularSurface)：Including two kinds of definition：Model Molecule surface and by solvent molecule
The surface that the track passed through when molecular surface is moved is formed.
Ribbon model is that large biological molecule visualizes one of most important model, and this is primarily due to it can effectively reflect life
The secondary structure information of thing molecule.Molecular surface model shows large biological molecule outward appearance on the whole, makes have visual understanding to it.
Meanwhile, the limitation of mobile terminal GPU performances, it is not suitable for showing the very many ball-and-stick models of gore number or Van der Waals model,
And the information content that wire-frame model can be showed is very little.In sum, we using in client real-time rendering ribbon model and
The method of translucent molecular surface model, the latter is additional on the former.This method can be relatively good display molecule structure
And three-dimensional appearance.
Ribbon modeling rendering：
The ribbon model geometric of protein is that, by the former molecular of main chain, and according to backbone atoms, we can build
Go out the contour curve of ribbon model.Contour curve can have various method for drafting.What Carson methods and protein chemistry were associated
Key point is the basis that planar unit of peptide is used as geometric modeling, and this method and the associated key point of computer graphics are
B-spline is used as producing the smooth regular curve of ribbon model.The method is widely used in protein ribbon model
Draw.Specific algorithm is as follows：
Define planar unit of peptide：The alpha carbon atoms and carboxyl oxygen for only needing to be input into a series of protein molecules for having sorted are former
Subcoordinate.The following is the method for defining planar unit of peptide (C α represent alpha-carbon atom)：
1. vector A=C α (i+l)-C α (i) is calculated
2. vector B=O (i)-C α (i) is calculated
3. multiplication cross obtains vectorial C=A × B
4. multiplication cross obtains vectorial D=C × A
5. couple vector C and D carries out unitization
Vectorial C is by the normal direction of the former molecular planar unit of peptide of C α (i), O (i), and C α (i+l).Vectorial D is parallel to planar unit of peptide
And perpendicular to vectorial A.
Axial coordinate in generation：The step for input be simulate ribbon required for interpolation count out, add for each
The assignment of the width of the amino acid of secondary structure.The following is define B-spline in axial coordinate the step of：
Find the midpoint P of Ca (i) and Ca (i+l).If this planar unit of peptide is a part for alpha spirals, along vectorial C
Direction translation point P, to away from helical axis direction movement half ribbon width respectively obtain point P (-)=P-D and P (+)
=P+D.
Line segment P (-) → P (+) is formed after being completed the step of above, its width is the ribbon that we want
Width and parallel to planar unit of peptide.These points are just evenly distributed on this line segment.
There is above-mentioned point coordinates, OpenGL ES storehouses just can be called to carry out ribbon modeling rendering.
Molecular surface model is drawn：
The drafting of three-dimensional molecular surface model, most critical is how to define molecular surface.Due to molecular surface border
Atom determine the shape and major function of molecule, therefore, it is increasingly important that the effective atom for judging molecule border just becomes.
A method among these is exactly to calculate a complete smooth surface on protein molecule surface atom.This curved surface is just
Referred to as molecular surface.
Solvent outer curved surface (solvent excluded surface, SES) method for drafting is the spy of R using a radius
Survey ball carries out the reach distance of rolling calculation molecular surface on molecule Van der Waals surface, and the surface model accuracy that it is calculated is most
It is high.But amount of calculation is larger.Real-time rendering cannot be accomplished.We draw surface using the Coarse method for drafting based on Gaussian Blur
Model, on the premise of drafting precision is reduced, three-dimensional molecular surface real-time rendering is realized in mobile terminal.
All actual tests of the invention are carried out on the mobile phone of pc simulators and the operation system of Android 4.3, and program can
Smoothness operation.
The technology contents that the present invention is not elaborated belong to the known technology of those skilled in the art.
Although being described to illustrative specific embodiment of the invention above, in order to the technology of the art
Personnel understand the present invention, it should be apparent that the invention is not restricted to the scope of specific embodiment, to the common skill of the art
For art personnel, as long as various change is in appended claim restriction and the spirit and scope of the present invention for determining, these
Change is it will be apparent that all utilize the innovation and creation of present inventive concept in the row of protection.
Claims (6)
1. a kind of mobile platform three dimensional biological molecular display method based on augmented reality, its feature is comprised the following steps：
Step (1), picture feature point are extracted：Plane picture on teaching material is taken pictures or scanned, by spy after extraction characteristic point
Point data storage is levied in service end；
Step (2), PDB file acquisitions and treatment：To each pictures, its corresponding protein structural information data is manually determined
PDB ID in storehouse, server is retrieved for No. ID with this PDB in protein structural information database, obtains PDB files laggard
Row is processed and is locally stored, and Image ID is associated with PDB files and picture relevant information；
Step (3), picture recognition：Mobile client captures the plane picture on teaching material using camera, after extracting characteristic point, with
The characteristic point that the certain intervals time will extract is uploaded onto the server, and the characteristic point with each pictures in step (1) carries out phase
Compare like degree, the picture in step (1) is abandoned if mismatching；Think to have recognized a mark if matching；Will correspondence
PDB files and relevant information be sent to mobile client；
Step (4), the drafting of three-dimensional separation flow：Sat in three-dimensional atomic point of the mobile client in the PDB files for obtaining
Mark, using OpenGL ES storehouses real-time rendering biomolecule C atomic framework ribbon models and molecular surface threedimensional model；
The Tracing Registration of step (5), view-based access control model mark：Mobile client end system is by the model of generation and movement in step (4)
The real background that client camera shoots is overlapped display；The displacement of mobile client camera space or rotation change
When system redraw window in real time, through coordinate transform real-time update visual angle, make observer can from it is arbitrarily angled and distance observation mould
Type.
2. the mobile platform three dimensional biological molecular display method based on augmented reality according to claim 1, its feature exists
In：Step (1) picture feature point is extracted, and is Scale-Invariant Feature Transform algorithms by based on SIFT
Improved SURF is Speeded Up Robust Features algorithms, finds image characteristic point, saves it in server.
3. the mobile platform three dimensional biological molecular display method based on augmented reality according to claim 2, its feature exists
In：PDB file acquisitions and treatment described in step (2), to each pictures in step (1), one PDB ID of manual specification
Number, retrieved from PDB servers using RCSB-PDB web services services, the PDB files to obtaining simplify treatment and
It is locally stored.
4. the mobile platform three dimensional biological molecular display method based on augmented reality according to claim 2, its feature exists
In：Picture recognition described in step (3), mobile client extracts picture feature with the Feature Points Extraction in step (1)
Dot matrix, uploads to service end at a time interval, and the characteristic point matrix in service end ergodic data storehouse carries out phase therewith
Compare like degree；Think that two images are matched when threshold value of the two images Feature Points Matching quantity more than setting.
5. the mobile platform three dimensional biological molecular display method based on augmented reality according to claim 2, its feature exists
In：The drafting of the three-dimensional separation flow described in step (4), uses OpenGL ES storehouses, the PDB files sent using server
Three-dimensional atomic coordinate information, draw biomolecule C atomic framework ribbon models and molecular surface threedimensional model.
6. the mobile platform three dimensional biological molecular display method based on augmented reality according to claim 2, its feature exists
In：The Tracing Registration of the view-based access control model mark described in step (5), the convex quadrangle illustration main body obtained according to image recognition
Four sides are that base determines that image affine coordinate system is set up in direction with original AR marks, so as to demarcate mobile client camera and main body
The spatial information of telltale mark, including position and attitude；Made in plot step (4) on view plane according to affine transformation matrix
Three-dimensional separation flow or interactive scene, finally merge with the real-time pictures of real scene and render, be displayed in mobile client
On screen；If there is picture additional information, it is shown together.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510033511.8A CN104537705B (en) | 2015-01-23 | 2015-01-23 | Mobile platform three dimensional biological molecular display system and method based on augmented reality |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510033511.8A CN104537705B (en) | 2015-01-23 | 2015-01-23 | Mobile platform three dimensional biological molecular display system and method based on augmented reality |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104537705A CN104537705A (en) | 2015-04-22 |
| CN104537705B true CN104537705B (en) | 2017-06-27 |
Family
ID=52853224
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510033511.8A Expired - Fee Related CN104537705B (en) | 2015-01-23 | 2015-01-23 | Mobile platform three dimensional biological molecular display system and method based on augmented reality |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104537705B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104794752B (en) * | 2015-04-30 | 2016-04-13 | 山东大学 | Based on virtual scene synergic modeling method and the system of mobile terminal and hologram display |
| CN105046213B (en) * | 2015-06-30 | 2019-03-12 | 塔普翊海（上海）智能科技有限公司 | A kind of method of augmented reality |
| CN105844979A (en) * | 2015-12-15 | 2016-08-10 | 齐建明 | Augmented reality book, and education system and method based on augmented reality book |
| CN106997366B (en) * | 2016-01-26 | 2020-05-15 | 视辰信息科技(上海)有限公司 | Database construction method, augmented reality fusion tracking method and terminal equipment |
| CN106372594A (en) * | 2016-08-30 | 2017-02-01 | 孟玲 | Mobile platform three-dimensional biological cell display system based on augmented reality |
| CN106445282B (en) * | 2016-09-08 | 2019-04-30 | 掌阅科技股份有限公司 | A kind of exchange method based on augmented reality |
| CN106650643B (en) * | 2016-12-06 | 2020-04-14 | 北京心有灵犀科技有限公司 | Method for making jewelry have augmented reality function |
| CN109471533B (en) * | 2018-11-09 | 2021-09-07 | 深圳职业技术学院 | Student end system in VR/AR classroom and use method thereof |
| WO2021004020A1 (en) * | 2019-12-20 | 2021-01-14 | 深圳晶泰科技有限公司 | System and method for use in user interaction in complex web3d scene |
| CN111191426B (en) * | 2020-01-08 | 2023-03-14 | 山东大学 | Data extraction and processing method based on Gaussian program output file |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2445189A2 (en) * | 2010-10-25 | 2012-04-25 | LG Electronics Inc. | Information processing apparatus and method thereof |
| CN103050025A (en) * | 2012-12-20 | 2013-04-17 | 广东欧珀移动通信有限公司 | Mobile terminal learning method and learning system thereof |
-
2015
- 2015-01-23 CN CN201510033511.8A patent/CN104537705B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2445189A2 (en) * | 2010-10-25 | 2012-04-25 | LG Electronics Inc. | Information processing apparatus and method thereof |
| CN103050025A (en) * | 2012-12-20 | 2013-04-17 | 广东欧珀移动通信有限公司 | Mobile terminal learning method and learning system thereof |
Non-Patent Citations (2)
| Title |
|---|
| Streaming mobile augmented reality on mobile phones;David M. Chen et al;《8th IEEE International Symposium on Mixed and Augmented Reality》;20091019;181-182 * |
| 移动增强现实型学习资源研究;王萍 等;《电化教育研究》;20131231(第12期);60-67 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104537705A (en) | 2015-04-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104537705B (en) | Mobile platform three dimensional biological molecular display system and method based on augmented reality | |
| CN111328396B (en) | Pose estimation and model retrieval for objects in images | |
| CN100470452C (en) | Method and system for implementing three-dimensional enhanced reality | |
| Bostanci et al. | Augmented reality applications for cultural heritage using Kinect | |
| CN111401266B (en) | Method, equipment, computer equipment and readable storage medium for positioning picture corner points | |
| Kropatsch et al. | Digital image analysis: selected techniques and applications | |
| CN110009561A (en) | A kind of monitor video target is mapped to the method and system of three-dimensional geographical model of place | |
| CN110246181B (en) | Anchor point-based attitude estimation model training method, attitude estimation method and system | |
| CN109242961A (en) | A kind of face modeling method, apparatus, electronic equipment and computer-readable medium | |
| CN112954292B (en) | Digital museum navigation system and method based on augmented reality | |
| CN113159232A (en) | Three-dimensional target classification and segmentation method | |
| CN109949900B (en) | Three-dimensional pulse wave display method and device, computer equipment and storage medium | |
| CN113688846B (en) | Object size recognition method, readable storage medium, and object size recognition system | |
| CN114219855A (en) | Point cloud normal vector estimation method and device, computer equipment and storage medium | |
| CN113240736A (en) | Pose estimation method and device based on YOLO6D improved network | |
| Yin et al. | [Retracted] Virtual Reconstruction Method of Regional 3D Image Based on Visual Transmission Effect | |
| Tsai et al. | Polygon‐based texture mapping for cyber city 3D building models | |
| CN116452757B (en) | Human body surface reconstruction method and system under complex scene | |
| Budianti et al. | Background blurring and removal for 3d modelling of cultural heritage objects | |
| CN108428250A (en) | A kind of X angular-point detection methods applied to vision positioning and calibration | |
| Zhao et al. | A smooth transition algorithm for adjacent panoramic viewpoints using matched delaunay triangular patches | |
| Dutreve et al. | Easy rigging of face by automatic registration and transfer of skinning parameters | |
| CN108268533A (en) | A kind of Image Feature Matching method for image retrieval | |
| CN113012298A (en) | Curved MARK three-dimensional registration augmented reality method based on region detection | |
| Gupta et al. | Image feature detection using an improved implementation of maximally stable extremal regions for augmented reality applications |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170627 Termination date: 20210123 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |