CN106846469A - The method and apparatus that feature based point tracking is reconstructed three-dimensional scenic by focusing storehouse - Google Patents
The method and apparatus that feature based point tracking is reconstructed three-dimensional scenic by focusing storehouse Download PDFInfo
- Publication number
- CN106846469A CN106846469A CN201710091014.2A CN201710091014A CN106846469A CN 106846469 A CN106846469 A CN 106846469A CN 201710091014 A CN201710091014 A CN 201710091014A CN 106846469 A CN106846469 A CN 106846469A
- Authority
- CN
- China
- Prior art keywords
- prime
- characteristic point
- storehouse
- dimensional scenic
- successful
- 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
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/08—Indexing scheme for image data processing or generation, in general involving all processing steps from image acquisition to 3D model generation
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses the method and apparatus that a kind of feature based point tracking is reconstructed three-dimensional scenic by focusing storehouse, including:The forward model that storehouse is focused on by three-dimensional scenic generation is set up, three-dimensional scenic characteristic point is given and is focused on the geometrical relationship of storehouse;The characteristic point for focusing on each image in storehouse is extracted, the coordinate of the characteristic point that the match is successful is followed the trail of, track of the characteristic point in storehouse is focused on is obtained;Set up the inverse model that three-dimensional scenic is reconstructed by focusing storehouse:By the characteristic point that the match is successful, the equation group on characteristic point three-dimensional coordinate is set up, the three-dimensional coordinate of characteristic point is obtained by solving equation group, reconstruct three-dimensional scenic, and realize that three-dimensional geometry is measured.Focusing storehouse of the invention is to fix detector, by the collection that focusing storehouse is completed along optical axis mobile lens, using the solution of the present invention, the three-dimensionalreconstruction under camera shooting visual angle can be realized, accurate three-dimensional structure information can be provided for virtual reality and dimensional measurement.
Description
Technical field
The present invention relates to computer vision and digital image processing field, more particularly to a kind of feature based point tracking is by gathering
Coke pile stack reconstructs three-dimensional scenic method and apparatus.
Background technology
The photo that traditional camera shoots be the light that sends of three-dimensional scenic by lens on two-dimensional detector light intensity it is tired
Plus and, so cause radiation direction information and depth information of scene to be compressed.It is research three emerging in recent years to calculate photography
The frontier of imaging is tieed up, it is one of method of three-dimensional scenic reconstruct in calculating photography to focus on storehouse.It is one group poly- to focus on storehouse
The burnt imaging sequence shot in different imaging planes or using different parameters, with abundant three-dimensional information.In computer vision
In, mainly carry out reconstruct and the dimensional measurement of three-dimensional scenic to focus on the degree for defocusing and focusing on of storehouse.It is existing by focusing on
The method of storehouse reconstruct three-dimensional scenic is the reconstructing method based on Focus field emission array (could also say that zoom method), it is necessary to calculate focusing
The Focus field emission array of each image of storehouse.
The content of the invention
It is an object of the invention to provide a kind of feature based point tracking by focusing storehouse reconstruct three-dimensional scenic method and
Device, the present invention uses tracing characteristic points to provide effective means by focusing storehouse reconstruct three-dimensional scenic, how visual is different from
Feel reconstruct three-dimensional scenic method, the present invention provide feature based point tracking by focusing storehouse reconstruct three-dimensional scenic method and
Device, it is no longer necessary to estimate camera internal reference and outer ginseng, disclosure satisfy that and shoot the angle of visual field (Field Of to camera in the prior art
View, FOV) under three-dimensional scenic reconstruct demand.
To achieve the above object, the present invention provides the side that a kind of feature based point tracking is reconstructed three-dimensional scenic by focusing storehouse
Method, methods described includes:The forward model that storehouse is focused on by three-dimensional scenic generation is set up, three-dimensional scenic characteristic point is obtained and is focused on
The relation of storehouse;The characteristic point of each image is extracted from the focusing storehouse, storehouse is being focused on just according to three-dimensional scenic generation
Drill the coordinate that the characteristic point that the match is successful in storehouse is focused on described in model tracking;Set up the three-dimensional coordinate of the characteristic point that the match is successful
With the equation group of three-dimensional scenic, the three-dimensional coordinate that equation group obtains the characteristic point that the match is successful is solved, reconstruct three-dimensional scenic.
Further, the forward model of the foundation is:
The three-dimensional scenic characteristic point with focus on storehouse relation be:
Wherein, (Sx,Sy) it is the object plane of scene, f (Sx,Sy) it is point (Sx,Sy) corresponding irradiation level, depth (Sx,Sy) be
The depth map of three-dimensional scenic, dnTo focus on the n-th imaging lens of storehouse to object plane (Sx,Sy) distance, d 'nTo focus on storehouse
I & lt imaging lens to detector distance, d '1To focus on the 1st imaging lens of storehouse to the distance of detector.
Further, the three-dimensional coordinate and the equation group of three-dimensional scenic for setting up the characteristic point that the match is successful, solution side
Journey group obtains the three-dimensional coordinate of the characteristic point that the match is successful, specifically includes:Set up the characteristic point abscissa and three-dimensional that the match is successful
The equation group of the depth map of scene, by solving least square problem, obtains the characteristic point abscissa that the match is successful;Set up matching
The equation group of the depth map of successful characteristic point ordinate and three-dimensional scenic, by solving least square problem, obtains matching into
The characteristic point ordinate of work(.
Further, the equation group of the depth map of the characteristic point abscissa and three-dimensional scenic:
Further, the equation group of the depth map of the characteristic point ordinate and three-dimensional scenic is:
The present invention also provides the device that a kind of feature based point tracking is reconstructed three-dimensional scenic by focusing storehouse, described device bag
Include:Module is built, the forward model of storehouse is focused on by three-dimensional scenic generation for setting up, three-dimensional scenic characteristic point is given and is focused on
The relation of storehouse;Acquisition module, the characteristic point for extracting each image from the focusing storehouse, follows the trail of the focusing storehouse
In the characteristic point that the match is successful;Reconstructed module, for the characteristic point that the match is successful according to acquisition module acquisition, builds
The three-dimensional coordinate and the equation group of three-dimensional scenic of the vertical characteristic point that the match is successful, solve equation group and obtain the characteristic point that the match is successful
Three-dimensional coordinate, reconstruct three-dimensional scenic.
Further, the forward model of the structure module foundation is:
The three-dimensional scenic characteristic point with focus on storehouse relation be:
Wherein, (Sx,Sy) it is the object plane of scene, f (Sx,Sy) it is point (Sx,Sy) corresponding irradiation level, depth (Sx,Sy) be
The depth map of three-dimensional scenic, dnTo focus on the n-th imaging lens of storehouse to object plane (Sx,Sy) distance, d 'nTo focus on storehouse
I & lt imaging lens to detector distance, d '1To focus on the 1st imaging lens of storehouse to the distance of detector.
Further, the reconstructed module is specifically included:First relation unit, it is horizontal for setting up the characteristic point that the match is successful
The equation group of the depth map of coordinate and three-dimensional scenic, by solving least square problem, obtains the horizontal seat of characteristic point that the match is successful
Mark;Second relation unit, for the foundation characteristic point ordinate that the match is successful and the equation group of the depth map of three-dimensional scenic, passes through
Least square problem is solved, the characteristic point ordinate that the match is successful is obtained;Reconfiguration unit, for according to first relation unit
The characteristic point abscissa that the match is successful is obtained, and second relation unit obtains the characteristic point ordinate that the match is successful,
Reconstruct three-dimensional scenic.
Further, the equation group of the depth map of the characteristic point abscissa and three-dimensional scenic:
Further, the equation group of the depth map of the characteristic point ordinate and three-dimensional scenic is:
The scheme that the present invention is provided, by the relation for building three-dimensional scenic characteristic point with focus on storehouse, follows the trail of and focuses on storehouse
In the characteristic point that the match is successful, and track of the tracking feature point in storehouse is focused on, and then realize camera and shoot under visual field
Three-dimensional scenic is reconstructed, and can provide accurate three-dimensional structure information for virtual reality and dimensional measurement.
Brief description of the drawings
Fig. 1 is that the feature based point tracking for providing according to a first embodiment of the present invention reconstructs three-dimensional scenic side by focusing storehouse
The schematic flow sheet of method.
Fig. 2 is the schematic diagram that the generation for providing according to a first embodiment of the present invention focuses on storehouse.
Fig. 3 is the n-th imaging process schematic diagram of the focusing storehouse for providing according to a first embodiment of the present invention.
Fig. 4 is that the feature based point tracking for providing according to a second embodiment of the present invention is filled by focusing storehouse reconstruct three-dimensional scenic
The structural representation put.
Specific embodiment
In the accompanying drawings, same or similar element is represented or with same or like function using same or similar label
Element.Embodiments of the invention are described in detail below in conjunction with the accompanying drawings.
In the description of the invention, term " " center ", " longitudinal direction ", " transverse direction ", "front", "rear", "left", "right", " vertical ",
The orientation or position relationship of the instruction such as " level ", " top ", " bottom " " interior ", " outward " are to be closed based on orientation shown in the drawings or position
System, is for only for ease of the description present invention and is described with simplified, must have rather than the device or element for indicating or imply meaning
Specific orientation, with specific azimuth configuration and operation, therefore it is not intended that limiting the scope of the invention.
As shown in figure 1, the feature based point tracking that the present embodiment is provided reconstructs three-dimensional scenic method bag by focusing storehouse
Include:
Step 101, sets up the forward model that storehouse is focused on by three-dimensional scenic generation, obtains three-dimensional scenic characteristic point and focuses on
The relation of storehouse.
In the step, it is one group of imaging sequence for focusing on different imaging planes or using different parameters to shoot to focus on storehouse
Row, the focusing storehouse in present embodiment is one group focuses on the imaging sequence of different imaging planes.Present embodiment is with along light
Axle mobile lens, while fixed detector complete focus on storehouse collection as a example by, illustrated to setting up forward model.By detection
Object (object is made up of multiple object points) focuses on the image sequence of different imaging surfaces, these image sequence shapes in device collection scene
Into focusing storehouse.It is many imaging planes imaging to the three-dimensional scenic under certain visual angle due to focusing on storehouse, it is thus possible to real
Existing camera shoots the three-dimensional scenic reconstruct under the angle of visual field (FOV), can provide accurate three-dimensional for virtual reality and dimensional measurement
Structural information.Certainly, the present invention can also focus on storehouse using the collection of other methods.
Consider to shoot the three-dimensional scenic under visual field in camera, (f (S can be usedx,Sy),depth(Sx,Sy)) description three-dimensional
Scene.Wherein, (Sx,Sy) it is the object plane of scene.f(Sx,Sy) it is point (Sx,Sy) corresponding irradiation level.depth(Sx,Sy) it is three-dimensional
The depth map of scene.
Fig. 2 is illustrated that the present embodiment forms the schematic diagram for focusing on storehouse, as shown in Fig. 2 the left side of Fig. 2 represents scene,
Right side represents detector, intermediate representation lens.Fixed detector, along optical axis mobile lens, the 1st time illustrated in such as Fig. 2 into
Picture ... n-th is imaged.As lens are along the movement of optical axis, the object plane of the corresponding scene of detector is also correspondingly moved along optical axis
The 1st object plane ... n-th object plane that be dynamic, being illustrated in such as Fig. 2.
Fig. 3 is the schematic diagram of the n-th imaging process for focusing on storehouse, as shown in figure 3, (Sx,Sy) for scene object plane, (x,
Y) it is n-th imaging surface, (Sx,Sy) dotted line Yu (x, y) between the plane where n-th imaging len.dnTo focus on storehouse
N-th imaging len is to object plane (Sx,Sy) distance, d 'nTo focus on the i & lt imaging len of storehouse to the distance of detector,
d′1To focus on the 1st imaging lens of storehouse to the distance of detector.
According to lens imaging principle, and lens imaging process is expressed using point spread function, set up and generated by three-dimensional scenic
Focus on storehouse forward model be:
Wherein,It is point (Sx,Sy) node expansion function on imaging surface (x, y).X and y be imaging surface abscissa and
Ordinate, physical significance is object point (Sx,Sy) the position coordinates in imaging surface.
In the present embodiment, for simplified model, it is considered to which the corresponding aperture of lens stop is approximately aperture, and imaging process is regarded as
Pinhole imaging system, can so cause to calculate simple with simplified model, therefore, node expansion functionIt is impulse function δ functions, then ties
Close the forward model stated:
It is as follows with the relation for focusing on storehouse to obtain three-dimensional scenic characteristic point:
And then obtain three-dimensional scenic characteristic point (Sx,Sy) focus on storehouse in equation of locus.
Step 102, extracts all of feature in each image from the focusing storehouse of the forward model described by step 101
Point, the forward model for focusing on storehouse according to three-dimensional scenic generation follows the trail of the coordinate of the characteristic point that the match is successful.
In practical application, it is possible to use (Scale-invariant feature transform, Scale invariant is special for SIFT
Levy conversion), ORB (ORiented Brief), SURF carry out the extraction of characteristic point and match.Matching refers to same object point and exists
Image space is different in different focusing storehouse pictures, and matching is exactly to find these points.
In specific implementation, it is contemplated that SIFT keeps stronger robustness to the visual angle change of image, noise, it is possible to locate
The matching problem in the case of translation, rotation, affine transformation between reason image, the present embodiment performs the figure for focusing on storehouse using SIFT
As matching, the characteristic point of the image that the match is successful is obtained.
In the step, all characteristic points in each image are extracted in the focusing storehouse obtained from step 101:feature_
1, feature_2 ..., feature_M, follow the trail of and focus on all feature point coordinates that the match is successful, characteristic point in storehouse
Feature_m is in the coordinate of n-th imaging surface for focusing on storehouse
Step 103:The inverse model that three-dimensional scenic is reconstructed by focusing storehouse is set up, the three of the characteristic point that the match is successful are obtained
Dimension coordinate, reconstructs three-dimensional scenic.
It refers to set up the three-dimensional of characteristic point that the match is successful to sit to set up by the inverse model of focusing storehouse reconstruct three-dimensional scenic
The equation group of mark and three-dimensional scenic.
The step method is specific as follows:
To the characteristic point feature_m that the match is successful, set up on characteristic point abscissa SxWith the depth map of three-dimensional scenic
depth(Sx,Sy) equation group:
Set up on characteristic point ordinate SyWith the depth map depth (S of three-dimensional scenicx,Sy) equation group:
On characteristic point abscissa SxWith the depth map depth (S of three-dimensional scenicx,Sy) equation group, be expressed as AX=b1,
X=(Sx,depth(Sx,Sy))TCan be by solving least square problem min | | AX | |2Obtain SxWith depth (Sx,Sy).It is same to close
In characteristic point ordinate SyWith depth (Sx,Sy) equation group, be expressed as AY=b2, Y=(Sy,depth(Sx,Sy))T
Can be by solving least square problem min | | AY | |2Obtain Sy。
In practical application, the three-dimensional scenic that generation camera is shot under visual field (FOV) includes three-dimensional point cloud atlas or three-dimensional rendering
Figure.
The method also includes:The distance between measurement characteristic point, there is provided the geometry range finding of three-dimensional scenic.
The method that the feature based point tracking that the present invention is provided is reconstructed three-dimensional scenic by focusing storehouse, by building three dimensional field
Scape characteristic point and the relation for focusing on storehouse, follow the trail of the characteristic point for focusing on that the match is successful in storehouse, and calculate the spy that the match is successful
Three-dimensional coordinate a little is levied, and then realizes the three-dimensional scenic reconstruct that camera is shot under visual field, can be that virtual reality and geometry are surveyed
Amount provides accurate three-dimensional structure information.
Referring to Fig. 4, a kind of feature based point tracking is the embodiment of the invention provides by focusing storehouse reconstruct three-dimensional scenic
Device, described device includes:
Module 201 is built, the forward model of storehouse is focused on by three-dimensional scenic generation for setting up, three-dimensional scenic feature is given
Point and the relation for focusing on storehouse;
Acquisition module 202, the characteristic point for extracting each image from storehouse is focused on, tracking is matched into focusing on storehouse
The characteristic point of work(;
Reconstructed module 203, for obtaining the characteristic point that the match is successful according to acquisition module 202, sets up what the match is successful
The three-dimensional coordinate of characteristic point and the equation group of three-dimensional scenic, solve the three-dimensional coordinate that equation group obtains the characteristic point that the match is successful,
Reconstruct three-dimensional scenic.
In above-mentioned implementation method, the forward model for building the foundation of module 201 is:
The three-dimensional scenic characteristic point with focus on storehouse relation be:
Wherein, (Sx,Sy) it is the object plane of scene, f (Sx,Sy) it is point (Sx,Sy) corresponding irradiation level, depth (Sx,Sy) be
The depth map of three-dimensional scenic, dnTo focus on the n-th imaging lens of storehouse to object plane (Sx,Sy) distance, d 'nTo focus on storehouse
I & lt imaging lens to detector distance, d '1To focus on the 1st imaging lens of storehouse to the distance of detector.
Acquisition module 202 extracts the feature of each image using SIFT, ORB or SURF method from the focusing storehouse
Point.
Reconstructed module 203 is specifically included:
First relation unit, for the foundation characteristic point abscissa that the match is successful and the equation of the depth map of three-dimensional scenic
Group, by solving least square problem, obtains the characteristic point abscissa that the match is successful;
Second relation unit, for the foundation characteristic point ordinate that the match is successful and the equation of the depth map of three-dimensional scenic
Group, by solving least square problem, obtains the characteristic point ordinate that the match is successful;
Reconfiguration unit for obtaining the characteristic point abscissa that the match is successful and described according to first relation unit
Second relation unit obtains the characteristic point ordinate that the match is successful, reconstructs three-dimensional scenic.
The characteristic point abscissa and the equation group of the depth map of three-dimensional scenic that first relation unit is obtained:
The characteristic point ordinate and the equation group of the depth map of three-dimensional scenic that second relation unit is obtained be:
In the embodiment of the present invention, the three-dimensional scenic of the reconstruct of reconstructed module 203 includes three-dimensional point cloud atlas or three-dimensional rendering figure.
The feature based point tracking that the present invention is provided is reconstructed the device of three-dimensional scenic by focusing storehouse, by building module structure
Build out three-dimensional scenic characteristic point and focus on the relation of storehouse, follow the trail of and focus on the characteristic point that the match is successful in storehouse, and calculate
Three-dimensional coordinate with successful characteristic point, and then the three-dimensional scenic reconstruct that camera is shot under visual field is realized, can be virtual existing
Real and dimensional measurement provides accurate three-dimensional structure information.
It is last it is to be noted that:The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations.This
The those of ordinary skill in field should be understood:Technical scheme described in foregoing embodiments can be modified, or it is right
Which part technical characteristic carries out equivalent;These modifications are replaced, and the essence of appropriate technical solution is departed from this
Invent the spirit and scope of each embodiment technical scheme.
Claims (10)
1. a kind of method that feature based point tracking is reconstructed three-dimensional scenic by focusing storehouse, it is characterised in that methods described includes:
The forward model that storehouse is focused on by three-dimensional scenic generation is set up, three-dimensional scenic characteristic point is obtained and is focused on the relation of storehouse;
The characteristic point of each image is extracted from the focusing storehouse, is chased after according to the forward model that three-dimensional scenic generation focuses on storehouse
The coordinate of the characteristic point that the match is successful in storehouse is focused on described in track;
The three-dimensional coordinate and the equation group of three-dimensional scenic of the characteristic point that the match is successful are set up, equation group is solved and is obtained what the match is successful
The three-dimensional coordinate of characteristic point, reconstructs three-dimensional scenic.
2. the method for claim 1, it is characterised in that the forward model of the foundation is:
The three-dimensional scenic characteristic point with focus on storehouse relation be:
Wherein, (Sx,Sy) it is the object plane of scene, f (Sx,Sy) it is point (Sx,Sy) corresponding irradiation level, depth (Sx,Sy) it is three-dimensional
The depth map of scene, dnTo focus on the n-th imaging lens of storehouse to object plane (Sx,Sy) distance, d 'nTo focus on the i-th of storehouse
Secondary imaging lens to detector distance, d '1To focus on the 1st imaging lens of storehouse to the distance of detector.
3. method as claimed in claim 1 or 2, it is characterised in that the three-dimensional coordinate of the foundation characteristic point that the match is successful
With the equation group of three-dimensional scenic, the three-dimensional coordinate that equation group obtains the characteristic point that the match is successful is solved, specifically included:
The equation group of the depth map of the foundation characteristic point abscissa that the match is successful and three-dimensional scenic, is asked by solving least square
Topic, obtains the characteristic point abscissa that the match is successful;
The equation group of the depth map of the foundation characteristic point ordinate that the match is successful and three-dimensional scenic, is asked by solving least square
Topic, obtains the characteristic point ordinate that the match is successful.
4. method as claimed in claim 3, it is characterised in that the side of the depth map of the characteristic point abscissa and three-dimensional scenic
Journey group:
5. method as claimed in claim 3, it is characterised in that the side of the depth map of the characteristic point ordinate and three-dimensional scenic
Cheng Zuwei:
6. a kind of feature based point tracking is reconstructed the device of three-dimensional scenic by focusing storehouse, it is characterised in that described device includes:
Module is built, the forward model of storehouse is focused on by three-dimensional scenic generation for setting up, three-dimensional scenic characteristic point is given and is gathered
The relation of coke pile stack;
Acquisition module, the characteristic point for extracting each image from the focusing storehouse, follows the trail of matching in the focusing storehouse
Successful characteristic point;
Reconstructed module, for the characteristic point that the match is successful according to acquisition module acquisition, sets up the spy that the match is successful
The equation group of three-dimensional coordinate and three-dimensional scenic a little is levied, the three-dimensional coordinate that equation group obtains the characteristic point that the match is successful is solved, weight
Structure three-dimensional scenic.
7. device as claimed in claim 6, it is characterised in that the forward model that the structure module is set up is:
The three-dimensional scenic characteristic point with focus on storehouse relation be:
Wherein, (Sx,Sy) it is the object plane of scene, f (Sx,Sy) it is point (Sx,Sy) corresponding irradiation level, depth (Sx,Sy) it is three-dimensional
The depth map of scene, dnTo focus on the n-th imaging lens of storehouse to object plane (Sx,Sy) distance, d 'nTo focus on the i-th of storehouse
Secondary imaging lens to detector distance, d '1To focus on the 1st imaging lens of storehouse to the distance of detector.
8. device as claimed in claims 6 or 7, it is characterised in that the reconstructed module is specifically included:
First relation unit, for the foundation characteristic point abscissa that the match is successful and the equation group of the depth map of three-dimensional scenic, leads to
Solution least square problem is crossed, the characteristic point abscissa that the match is successful is obtained;
Second relation unit, for the foundation characteristic point ordinate that the match is successful and the equation group of the depth map of three-dimensional scenic, leads to
Solution least square problem is crossed, the characteristic point ordinate that the match is successful is obtained;
Reconfiguration unit, for obtaining the characteristic point abscissa that the match is successful, and described second according to first relation unit
Relation unit obtains the characteristic point ordinate that the match is successful, reconstructs three-dimensional scenic.
9. device as claimed in claim 8, it is characterised in that the side of the depth map of the characteristic point abscissa and three-dimensional scenic
Journey group:
10. device as claimed in claim 8, it is characterised in that the depth map of the characteristic point ordinate and three-dimensional scenic
Equation group is:
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2016111547529 | 2016-12-14 | ||
CN201611154752 | 2016-12-14 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106846469A true CN106846469A (en) | 2017-06-13 |
CN106846469B CN106846469B (en) | 2019-12-03 |
Family
ID=59128734
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710091014.2A Active CN106846469B (en) | 2016-12-14 | 2017-02-20 | Based on tracing characteristic points by the method and apparatus of focusing storehouse reconstruct three-dimensional scenic |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106846469B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113034490A (en) * | 2021-04-16 | 2021-06-25 | 北京石油化工学院 | Method for monitoring stacking safety distance of chemical storehouse |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101432776A (en) * | 2006-05-05 | 2009-05-13 | 汤姆森特许公司 | System and method for three-dimensional object reconstruction from two-dimensional images |
KR100983548B1 (en) * | 2010-04-12 | 2010-09-24 | 이화여자대학교 산학협력단 | A 3d shape reconstruction method considering point spread function of a microscope |
CN103440679A (en) * | 2013-08-09 | 2013-12-11 | 中国科学院苏州生物医学工程技术研究所 | Three-dimensional reconstruction method for confocal laser scanning microscopic image |
CN104463949A (en) * | 2014-10-24 | 2015-03-25 | 郑州大学 | Rapid three-dimensional reconstruction method and system based on light field digit refocusing |
CN105023275A (en) * | 2015-07-14 | 2015-11-04 | 清华大学 | Super-resolution light field acquisition device and three-dimensional reconstruction method thereof |
CN105279789A (en) * | 2015-11-18 | 2016-01-27 | 中国兵器工业计算机应用技术研究所 | A three-dimensional reconstruction method based on image sequences |
-
2017
- 2017-02-20 CN CN201710091014.2A patent/CN106846469B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101432776A (en) * | 2006-05-05 | 2009-05-13 | 汤姆森特许公司 | System and method for three-dimensional object reconstruction from two-dimensional images |
KR100983548B1 (en) * | 2010-04-12 | 2010-09-24 | 이화여자대학교 산학협력단 | A 3d shape reconstruction method considering point spread function of a microscope |
CN103440679A (en) * | 2013-08-09 | 2013-12-11 | 中国科学院苏州生物医学工程技术研究所 | Three-dimensional reconstruction method for confocal laser scanning microscopic image |
CN104463949A (en) * | 2014-10-24 | 2015-03-25 | 郑州大学 | Rapid three-dimensional reconstruction method and system based on light field digit refocusing |
CN105023275A (en) * | 2015-07-14 | 2015-11-04 | 清华大学 | Super-resolution light field acquisition device and three-dimensional reconstruction method thereof |
CN105279789A (en) * | 2015-11-18 | 2016-01-27 | 中国兵器工业计算机应用技术研究所 | A three-dimensional reconstruction method based on image sequences |
Non-Patent Citations (3)
Title |
---|
DONGBO ZHANG 等: "Plant Three-dimensional Information Detection Based on Single Moving Camera", 《INTERNATIONAL CONFERENCE ON COMPUTER, COMMUNICATIONS AND INFORMATION TECHNOLOGY》 * |
赵兴荣 等: "基于光场相机的超分辨焦点堆栈的研究", 《计算机测量与控制》 * |
陈佃文: "基于4D光场数据的深度信息获取", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113034490A (en) * | 2021-04-16 | 2021-06-25 | 北京石油化工学院 | Method for monitoring stacking safety distance of chemical storehouse |
CN113034490B (en) * | 2021-04-16 | 2023-10-10 | 北京石油化工学院 | Stacking safety distance monitoring method for chemical warehouse |
Also Published As
Publication number | Publication date |
---|---|
CN106846469B (en) | 2019-12-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104463949B (en) | A kind of quick three-dimensional reconstructing method and its system based on light field numeral refocusing | |
CN103971353B (en) | Splicing method for measuring image data with large forgings assisted by lasers | |
CN104408732B (en) | A kind of big depth of field measuring system and method based on omnidirectional's structure light | |
CN103971406B (en) | Submarine target three-dimensional rebuilding method based on line-structured light | |
CN106908622A (en) | A kind of chromatography PIV measurement apparatus and method based on optical field imaging | |
CN108428255A (en) | A kind of real-time three-dimensional method for reconstructing based on unmanned plane | |
US20170140578A1 (en) | Depth camera-based human-body model acquisition method and network virtual fitting system | |
CN104034305B (en) | A kind of monocular vision is the method for location in real time | |
CN105931234A (en) | Ground three-dimensional laser scanning point cloud and image fusion and registration method | |
CN106097348A (en) | A kind of three-dimensional laser point cloud and the fusion method of two dimensional image | |
CN106875436A (en) | A kind of feature based dot density by focusing storehouse estimating depth method and apparatus | |
CN106971408A (en) | A kind of camera marking method based on space-time conversion thought | |
CN107633532B (en) | Point cloud fusion method and system based on white light scanner | |
CN1897715A (en) | Three-dimensional vision semi-matter simulating system and method | |
CN104063860A (en) | Method for refining edge of laser-point cloud | |
CN111899345B (en) | Three-dimensional reconstruction method based on 2D visual image | |
CN108010125A (en) | True scale three-dimensional reconstruction system and method based on line structure light and image information | |
CN104036541A (en) | Fast three-dimensional reconstruction method in vision measurement | |
CN106017327A (en) | Structural light measurement sensor calibration method | |
CN107103621A (en) | Non- cooperative Spacecraft three-dimensional pose measuring system based on light field one camera | |
CN110455281A (en) | Dark small and weak celestial body optics navigation characteristic Imaging Simulation method | |
CN103617631B (en) | A kind of tracking based on Spot detection | |
CN104166995B (en) | Harris-SIFT binocular vision positioning method based on horse pace measurement | |
CN101661623B (en) | Three-dimensional tracking method of deformable body based on linear programming | |
CN105488780A (en) | Monocular vision ranging tracking device used for industrial production line, and tracking method thereof |
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 |