CN106780743A - It is a kind of remotely to match somebody with somebody spoon method and system - Google Patents
It is a kind of remotely to match somebody with somebody spoon method and system Download PDFInfo
- Publication number
- CN106780743A CN106780743A CN201611177790.6A CN201611177790A CN106780743A CN 106780743 A CN106780743 A CN 106780743A CN 201611177790 A CN201611177790 A CN 201611177790A CN 106780743 A CN106780743 A CN 106780743A
- Authority
- CN
- China
- Prior art keywords
- key
- image
- somebody
- dimensional
- billet
- 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
- 238000000034 method Methods 0.000 title claims abstract description 42
- 239000000284 extract Substances 0.000 claims abstract description 12
- 238000010146 3D printing Methods 0.000 claims abstract description 9
- 238000000605 extraction Methods 0.000 claims abstract description 6
- 238000007639 printing Methods 0.000 claims abstract description 4
- 238000012545 processing Methods 0.000 claims description 23
- 230000008569 process Effects 0.000 claims description 14
- 230000009466 transformation Effects 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims 1
- 238000005516 engineering process Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000000739 chaotic effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000011840 criminal investigation Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000008570 general process Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000007493 shaping process Methods 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
- G06T17/20—Finite element generation, e.g. wire-frame surface description, tesselation
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B33—ADDITIVE MANUFACTURING TECHNOLOGY
- B33Y—ADDITIVE MANUFACTURING, i.e. MANUFACTURING OF THREE-DIMENSIONAL [3-D] OBJECTS BY ADDITIVE DEPOSITION, ADDITIVE AGGLOMERATION OR ADDITIVE LAYERING, e.g. BY 3-D PRINTING, STEREOLITHOGRAPHY OR SELECTIVE LASER SINTERING
- B33Y50/00—Data acquisition or data processing for additive manufacturing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/80—Geometric correction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20172—Image enhancement details
- G06T2207/20192—Edge enhancement; Edge preservation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Chemical & Material Sciences (AREA)
- Manufacturing & Machinery (AREA)
- Materials Engineering (AREA)
- Image Processing (AREA)
- Processing Or Creating Images (AREA)
Abstract
Remotely match somebody with somebody spoon method and system the invention discloses a kind of, comprise the following steps：Set up key billet database, storing keys mold type and moulded dimension parameter；Collection key image；Treatment key image, the key image of collection is processed, and eliminates shooting distance caused ratio distortion different with shooting angle；Extract key image tooth profile；Three-dimensional key geometrical model is set up, the key profile of extraction is combined the three-dimensional key geometrical model of foundation with key billet type；Printing key, entity is processed into using 3D printing technique by three-dimensional key geometrical model.The present invention is long-range to need not rely on the identification of tooth form code and camera demarcation with spoon, and precision reaches unlocking and requires.
Description
Technical field
The present invention relates to bitting field, spoon method and system are remotely matched somebody with somebody in particular to a kind of.
Background technology
2008, the scholar such as B Laxton, K Wang, the S Savage in University of California Santiago branch school passed through high-resolution
Rate camera and telescope have collected the key image outside 50 meters, and contours extract and tooth form code identification are carried out to it, obtain
The tooth form code of key（As shown in Figure 1）, final conjunction gear shape code and saltation layer Special forming equipment are added to key billet
Work obtains key（As shown in Figure 2）, reach the long-range purpose with spoon.The key high precision processed with the method, it is highly reliable,
But because Now Domestic key bit shape code species is various, design standard is chaotic, and the method is difficult to promote at home.
The binocular vision technology started with Robert et al. simultaneously can avoid tooth form code and be difficult to know with reference to 3D printing technique
Other problem, its general process is to shoot two width or multiple image to same key using two video cameras, constitutes cubic phase
It is right, recycle the parallax of corresponding points to calculate steric information, the threedimensional model of key in image is then reconstructed, finally using 3D
Printing technique processes the key based on threedimensional model.But for spoon is remotely matched somebody with somebody, the technology also has the defect of itself, accurately
Reconstructing three-dimensional model need to demarcate video camera, and photo is shot as background using special scaling board, and remotely match somebody with somebody
Spoon be to the requirement that shoots photo without any fixed background, therefore long-range under the conditions of demarcating be with spoon it is skimble-skamble,
And use the threedimensional model precision of the complicated key of the threedimensional model precision particularly tooth form that un-calibrated method is rebuild well below
Use requirement, i.e., cannot be unlocked based on the key that the mould processing goes out, therefore, long-range using un-calibrated method remains unchanged in the least with spoon
It is meaningless.
The content of the invention
The purpose of the present invention designs one kind and needs not rely on the identification of tooth form code and take the photograph aiming at the deficiencies in the prior art
Camera calibration and precision reach unlock require based on image processing techniques and 3D printing technique remotely with key system.
To achieve these goals, the one kind designed by the present invention remotely matches somebody with somebody spoon method, and it is characterized in that, including with
Lower step：
S1 sets up key billet database, storing keys mold type and moulded dimension parameter；
S2 gathers key image；
S3 processes key image, and the key image of collection is processed, and eliminates shooting distance different with shooting angle caused
Ratio distortion；
S 4 extracts key picture tooth profile；
S5 sets up three-dimensional key geometrical model, and the key profile of extraction is combined into the three-dimensional key geometry mould of foundation with key billet type
Type；
S6 prints key, and three-dimensional key geometrical model is processed into entity using 3D printing technique.
Further, to obtain high-quality picture, the success rate reduction shooting restrictive condition that key is rebuild is improved, it is described
Also include pretreatment key image in step S2, specially：Key image after collection is first carried out into gray proces, then is carried out low
Pass filter treatment, makes pixel more smooth, and eliminates the reflective patch for causing, while reaching noise reduction purpose and using non-maximum
Suppress to eliminate the shade of gray at non-edge, make image edge clear, improve picture quality.
Further, the step S3 detailed processes are：Feature first is carried out to the key image for gathering with reference to key billet
Point matching, then coordinate transform is carried out to key image using projective transformation algorithm, eliminate due to shooting angle and shooting distance not
The ratio distortion caused by.
Yet further, the detailed process of the step S4 is：Calculated with Hough transform and linear search golden section
Method, searches for and extracts the tooth profile of key, and interpolation processing is carried out to tooth profile with Lagrange's interpolation, improves wheel
Wide definition.
Yet further, the detailed process of the step S5 is：According to the shaped as key bit profile for extracting, with reference in database
The length and width dimensional parameters generation two-dimensional discrete point cloud of the key billet of extraction, sits in conjunction with key billet thickness and gullet depth extension
Mark dimension generation three-dimensional point cloud model, and three-dimensional point cloud is converted into by 3-D geometric model by a cloud and surface reconstruction.
A kind of remotely to match somebody with somebody key system, it is characterized in that：Including image capture module, key billet DBM, figure
As processing module, three-dimensional reconstruction module and 3D printer；
Described image acquisition module, for gathering key photo to be reconstructed；
The key billet DBM is connected with image processing module and three-dimensional reconstruction module respectively, for setting up key billet number
According to storehouse, storing keys mold type and moulded dimension parameter；
Described image processing module is connected with image capture module, for processing the key image for being gathered, eliminates and claps
Ratio distortion caused by photographic range is different with shooting angle, and extract key image tooth profile；
The three-dimensional reconstruction module is connected with image processing module, for combining shaped as key bit and key billet data genaration key three
Dimension geometrical model；
The 3D printer is connected with three-dimensional reconstruction module, for receiving key 3-D geometric model and printing key entity.
Further, described image acquisition module includes CCD camera and image pick-up card.The CCD camera is used for
Key image is shot, described image capture card is used for the image information collecting for obtaining CCD camera shooting and transmits to image
Processing module.
The advantage of the invention is that：
1st, image quality is improved with image processing techniques, can effectively reduces key photo acquisition difficulty；
2nd, ratio distortion is eliminated with image registration techniques, can effectively expands shooting angle, further reduce key photo acquisition
Difficulty；
3rd, set up key billet model database so that the system has good scalability, effectively extend being applicable for the system
Scope；The key model of the high accuracy key billet Model Reconstruction based on storage is compared to the key rebuild with binocular vision method
Model possesses precision higher.
4th, key 3-D geometric model is set up by way of key billet model is combined tooth profile and has both evaded tooth
The problem that shape code is difficult to improves model accuracy again；
If the 5, being processed shaping with 3D printing technique pair model, speed is fast, and difficulty is low, the key entity precision of processing
It is high.
Brief description of the drawings
Fig. 1 is a kind of long-range structured flowchart with key system of the present invention.
Fig. 2 is key three-dimensional point cloud atlas.
Fig. 3 is key 3-D geometric model structural representation.
Specific embodiment
The present invention is described in further detail with specific embodiment below in conjunction with the accompanying drawings：
It is a kind of remotely to match somebody with somebody spoon method, comprise the following steps：
S1 sets up key billet database, storing keys mold type and moulded dimension parameter；
S2 gathers key image；
S3 processes key image, and the key image of collection is processed, and eliminates shooting distance different with shooting angle caused
Ratio distortion；
S 4 extracts key image tooth profile；
S5 sets up three-dimensional key geometrical model, and the key profile of extraction is combined into the three-dimensional key geometry mould of foundation with key billet type
Type；
S6 prints key, and three-dimensional key geometrical model is processed into entity using 3D printing technique.
Wherein, key billet database is set up, including sets up the database comprising various types of key billet model and dimensional parameters,
For key image registration provides registering material and length and width, thickness, tooth depth d and cross section radian equidimension information, use
When can directly extract.And wherein data can be updated, increase, delete etc. with operation, increase key billet data storage species simultaneously
Repeated data is reduced, to meet use requirement.
To obtain high-quality image, the success rate reduction shooting restrictive condition that key is rebuild is improved, in the step S2
Also include pretreatment key image, specially：Key image after collection is first carried out into gray proces, then is carried out at LPF
Reason, makes pixel more smooth, and eliminates the reflective patch for causing, while reaching noise reduction purpose and being eliminated using non-maxima suppression
Shade of gray at non-edge, makes image edge clear, improves picture quality.
Step S3 detailed processes are：Key billet model picture is extracted from key billet database, by key image to be reconstructed
Registering, solution transformation matrix, it is considered to which the visual angle of key different parts is different, using projective transformation algorithm to key figure is carried out with it
As carrying out coordinate transform, whether there is curved surface to select to use plane projection algorithm or curved surface projection algorithm to eliminate according to key entity
Due to shooting angle caused ratio distortion different with shooting distance.Gained key picture is converted with projective transformation algorithm to compare
Other conversion arithmetic accuracies are higher.
The detailed process of step S4 is：With Hough transform and linear search golden cut algorithm, according to pixel in image
Brightness step is searched for and extracts the tooth profile of key, and carries out interpolation processing to tooth profile with Lagrange's interpolation,
Improve contour sharpness and smoothness.
The detailed process of step S5 is：According to the shaped as key bit profile for extracting, with reference to the key billet extracted in database
Length and width dimensional parameters generate two-dimensional discrete point cloud, three-dimensional in conjunction with key billet thickness and gullet depth extension coordinate dimensions generation
Point cloud model, and triangular network is divided by a cloud, tri patch is generated, tri patch is connected with surface reconstruction is given birth to
Into 3-D geometric model.
The detailed process of step S6 is：Key 3-D geometric model is converted into stl file formats and 3D printer is imported.
Model cut into slices by 3D printer and planned printer head running orbit, key entity is obtained eventually through 3D printing,
The entity precision and intensity reach unlocking and require.
It is as depicted a kind of remotely with key system, including image capture module, key billet DBM, image procossing
Module, three-dimensional reconstruction module and 3D printer；
Described image acquisition module, for gathering key photo to be reconstructed；
The key billet DBM is connected with image processing module and three-dimensional reconstruction module respectively, for setting up key billet number
According to storehouse, storing keys mold type and moulded dimension parameter；
Described image processing module is connected with image capture module, for processing the key image for being gathered, eliminates and claps
Ratio distortion caused by photographic range is different with shooting angle, and extract key image tooth profile；
The three-dimensional reconstruction module is connected with image processing module, for combining shaped as key bit and key billet data genaration key three
Dimension geometrical model；
The 3D printer is connected with three-dimensional reconstruction module, for receiving key 3-D geometric model and printing key entity.
Wherein, image capture module system includes CCD camera and image pick-up card.CCD camera is used to shoot key
Image, described image capture card is used for the image information collecting for obtaining CCD camera shooting and transmits to image processing module.
The system application field can be divided into civilian and police, run into go out and leave behind the situation of key and can be shone by key
Piece goes out the key that can be opened the door with the system print, is resident's provides convenient；Meeting technology unlocking in criminal investigation cannot
The lockset of opening can obtain required key of unlocking by shooting key photo, and more easily approach is provided to unlock.The system
20 meters or so the key photos apart from various angles can be processed.
Claims (7)
1. it is a kind of remotely to match somebody with somebody spoon method, it is characterised in that to comprise the following steps：
S1 sets up key billet database, storing keys mold type and moulded dimension parameter；
S2 gathers key image；
S3 processes key image, and the key image of collection is processed, and eliminates shooting distance different with shooting angle caused
Ratio distortion；
S4 extracts key image tooth profile；
S5 sets up three-dimensional key geometrical model, and the key profile of extraction is combined into the three-dimensional key geometry mould of foundation with key billet type
Type；
S6 prints key, and three-dimensional key geometrical model is processed into entity using 3D printing technique.
It is 2. according to claim 1 remotely to match somebody with somebody spoon method, it is characterised in that：Also include pretreatment key figure in step S2
Picture, specially：Key image after collection is first carried out into gray proces, then carries out low-pass filtering treatment, and use non-maximum
Suppress to eliminate the shade of gray at non-edge.
It is 3. according to claim 2 remotely to match somebody with somebody spoon method, it is characterised in that：The step S3 detailed processes are：First combine
Key billet carries out Feature Points Matching to the key image for gathering, then carries out coordinate change to key image using projective transformation algorithm
Change, eliminate due to shooting angle caused ratio distortion different with shooting distance.
It is 4. according to claim 3 remotely to match somebody with somebody spoon method, it is characterised in that：The detailed process of the step S4 is：With
Hough transform and linear search golden cut algorithm, search for and extract the tooth profile of key, and use Lagrange's interpolation
Interpolation processing is carried out to tooth profile, contour sharpness is improved.
It is 5. according to claim 1 remotely to match somebody with somebody spoon method, it is characterised in that：The detailed process of the step S5 is：According to
The shaped as key bit profile of extraction, two-dimensional discrete point cloud is generated with reference to the length and width dimensional parameters of the key billet extracted in database, then
With reference to key billet thickness and gullet depth extension coordinate dimensions generation three-dimensional point cloud model, and by a cloud and surface reconstruction
Three-dimensional point cloud is converted into 3-D geometric model.
It is 6. a kind of remotely to match somebody with somebody key system, it is characterised in that：Including image capture module, key billet DBM, image procossing
Module, three-dimensional reconstruction module and 3D printer；
Described image acquisition module, for gathering key photo to be reconstructed；
The key billet DBM is connected with image processing module and three-dimensional reconstruction module respectively, for setting up key billet number
According to storehouse, storing keys mold type and moulded dimension parameter；
Described image processing module is connected with image capture module, for processing the key image for being gathered, eliminates and claps
Ratio distortion caused by photographic range is different with shooting angle, and extract key image tooth profile；
The three-dimensional reconstruction module is connected with image processing module, for combining shaped as key bit and key billet data genaration key three
Dimension geometrical model；
The 3D printer is connected with three-dimensional reconstruction module, for receiving key 3-D geometric model and printing key entity.
It is 7. a kind of remotely to match somebody with somebody key system, it is characterised in that：Described image acquisition module system includes CCD camera and IMAQ
Card, the CCD camera is used to shoot key image, and described image capture card is used to shoot CCD camera the image for obtaining
Information gathering is simultaneously transmitted to image processing module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611177790.6A CN106780743B (en) | 2016-12-19 | 2016-12-19 | It is a kind of remotely to match spoon method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611177790.6A CN106780743B (en) | 2016-12-19 | 2016-12-19 | It is a kind of remotely to match spoon method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106780743A true CN106780743A (en) | 2017-05-31 |
| CN106780743B CN106780743B (en) | 2018-06-29 |
Family
ID=58890157
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611177790.6A Active CN106780743B (en) | 2016-12-19 | 2016-12-19 | It is a kind of remotely to match spoon method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106780743B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107931606A (en) * | 2017-11-07 | 2018-04-20 | 昆明理工大学 | A kind of bitting device and method |
| CN109345678A (en) * | 2018-11-30 | 2019-02-15 | 四川研宝科技有限公司 | A kind of smart lock open method and system |
| CN109794728A (en) * | 2019-03-25 | 2019-05-24 | 湖南森普罗科技有限公司 | A kind of system and method configuring special-section key |
| CN109949402A (en) * | 2017-12-20 | 2019-06-28 | 艾迪普（北京）文化科技股份有限公司 | Threedimensional model generation method based on image recognition |
| CN113310414A (en) * | 2021-06-01 | 2021-08-27 | 北京远鸥科技有限公司 | Key image tooth profile rapid measurement and definition method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101030300A (en) * | 2007-02-08 | 2007-09-05 | 深圳大学 | Method for matching depth image |
| US20120224755A1 (en) * | 2011-03-02 | 2012-09-06 | Andy Wu | Single-Action Three-Dimensional Model Printing Methods |
| CN103198751A (en) * | 2013-03-06 | 2013-07-10 | 南京邮电大学 | Line feature map creation method of mobile robot based on laser range finder |
| CN103473021A (en) * | 2013-07-10 | 2013-12-25 | 杭州安致文化创意有限公司 | Two-dimensional-image-based 3D (three-dimensional) printing system and method |
| CN104484648A (en) * | 2014-11-27 | 2015-04-01 | 浙江工业大学 | Variable-viewing angle obstacle detection method for robot based on outline recognition |
-
2016
- 2016-12-19 CN CN201611177790.6A patent/CN106780743B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101030300A (en) * | 2007-02-08 | 2007-09-05 | 深圳大学 | Method for matching depth image |
| US20120224755A1 (en) * | 2011-03-02 | 2012-09-06 | Andy Wu | Single-Action Three-Dimensional Model Printing Methods |
| CN103198751A (en) * | 2013-03-06 | 2013-07-10 | 南京邮电大学 | Line feature map creation method of mobile robot based on laser range finder |
| CN103473021A (en) * | 2013-07-10 | 2013-12-25 | 杭州安致文化创意有限公司 | Two-dimensional-image-based 3D (three-dimensional) printing system and method |
| CN104484648A (en) * | 2014-11-27 | 2015-04-01 | 浙江工业大学 | Variable-viewing angle obstacle detection method for robot based on outline recognition |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107931606A (en) * | 2017-11-07 | 2018-04-20 | 昆明理工大学 | A kind of bitting device and method |
| CN109949402A (en) * | 2017-12-20 | 2019-06-28 | 艾迪普（北京）文化科技股份有限公司 | Threedimensional model generation method based on image recognition |
| CN109345678A (en) * | 2018-11-30 | 2019-02-15 | 四川研宝科技有限公司 | A kind of smart lock open method and system |
| CN109794728A (en) * | 2019-03-25 | 2019-05-24 | 湖南森普罗科技有限公司 | A kind of system and method configuring special-section key |
| CN113310414A (en) * | 2021-06-01 | 2021-08-27 | 北京远鸥科技有限公司 | Key image tooth profile rapid measurement and definition method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106780743B (en) | 2018-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106780743B (en) | It is a kind of remotely to match spoon method and system | |
| CN105120257B (en) | A kind of vertical depth sensing device based on structure light coding | |
| CN105313782B (en) | Vehicle travel assist system and its method | |
| CN106203342A (en) | Target identification method based on multi-angle local feature coupling | |
| CN105303616B (en) | Embossment modeling method based on single photo | |
| CN103679707A (en) | Binocular camera disparity map based road obstacle detection system and method | |
| CN101887589A (en) | Stereoscopic vision-based real low-texture image reconstruction method | |
| CN102411779B (en) | Object model matching posture measuring method based on image | |
| CN103345736A (en) | Virtual viewpoint rendering method | |
| CN110211169B (en) | Reconstruction method of narrow baseline parallax based on multi-scale super-pixel and phase correlation | |
| CN103886611A (en) | Image matching method suitable for automatically detecting flight quality of aerial photography | |
| CN104346833A (en) | Vehicle restructing algorithm based on monocular vision | |
| CN106023147B (en) | The method and device of DSM in a kind of rapidly extracting linear array remote sensing image based on GPU | |
| CN108537865A (en) | A kind of the pseudo-classic architecture model generation method and device of view-based access control model three-dimensional reconstruction | |
| CN108460795A (en) | Inverted pyramid formula binocular solid matching process and system | |
| CN116449384A (en) | Radar inertial tight coupling positioning mapping method based on solid-state laser radar | |
| CN109059868A (en) | A kind of binocular distance measuring method based on Adaptive matching window | |
| Wendel et al. | Automatic alignment of 3D reconstructions using a digital surface model | |
| CN117115336A (en) | Point cloud reconstruction method based on remote sensing stereoscopic image | |
| CN111325828A (en) | Three-dimensional face acquisition method and device based on three-eye camera | |
| CN110889868B (en) | Monocular image depth estimation method combining gradient and texture features | |
| CN102175227B (en) | Quick positioning method for probe car in satellite image | |
| CN104299223B (en) | Different-source image matching method based on Gabor coding | |
| CN116878524A (en) | Dynamic SLAM dense map construction method based on pyramid L-K optical flow and multi-view geometric constraint | |
| CN106355595A (en) | Stereo vision matching method for target images |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Li Hui Inventor after: Shen Shengnan Inventor after: Dai Xiangyu Inventor after: Li Wei Inventor after: Liu Sen Inventor after: Cai Mang Inventor after: Huang Yicang Inventor after: Zhou Xingying Inventor before: Li Hui Inventor before: Shen Shengnan Inventor before: Dai Xiangyu Inventor before: Li Wei Inventor before: Liu Sen Inventor before: Cai Mang |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |